{"items":[{"id":"019e4855-87c2-7500-bff1-886594a779a8","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/logo-inpaint","name":"Logo Inpaint","description":"Place a logo onto a target image, with optional mask to constrain placement. When the mask is omitted, the workflow picks a placement automatically.","version":"2.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/logo-inpaint/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["logo placement","optional mask control","per-image billing"],"content":null,"pricing_note":null,"created_at":"2026-05-21T02:20:25.414423Z","updated_at":"2026-05-21T23:42:57.078584Z"},{"id":"019e03a5-eb53-7b82-9b07-09250daa768e","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/object-removal/prompt","name":"Object Removal (Prompt)","description":"Remove requested objects from a photo using a short text instruction. Flux-fill restores the background without requiring a mask.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/object-removal/card-candidate-11.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Prompt Object Removal API: text-guided photo cleanup | Runflow","keywords":["prompt object removal","text guided object removal","remove object","image inpainting","photo cleanup","object erase","AI image editing","image to image","Flux fill","Runflow","API"],"description":"Remove requested objects from a photo with a short text prompt. Flux-fill rebuilds the background with fixed per-image pricing."},"notable_features":["Prompt-driven object removal","Flux-fill backbone for clean inpaint","Per-image billing"],"content":"## Overview\n\n**Object Removal (Prompt)** removes requested objects from a photo using a short text instruction. Describe what should be removed, and the workflow rebuilds the cleaned area to match the surrounding image.\n\n## How it works\n\nSend the source photo package and a concise prompt such as \"remove glasses and laptop\" or \"remove jacket\". Keep the prompt short and concrete; the public API accepts up to 7 words. The workflow returns the cleaned image through the standard Runflow output contract.\n\n## Common use cases\n\n- Removing props or distractions without hand-drawing a mask\n- Cleaning portraits and lifestyle images\n- Preparing product and marketing images at scale\n- Fast photo cleanup from natural-language instructions\n","pricing_note":null,"created_at":"2026-05-07T18:14:25.875995Z","updated_at":"2026-05-07T18:21:50.173113Z"},{"id":"019e02fd-df44-78a0-a3f6-f55c4002c442","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/smart-segmentation","name":"Smart Segmentation","description":"Segment a requested subject from an image using the SAM3 VLM workflow. Returns one or more mask/segmentation outputs from a prompt-guided image analysis pass.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/smart-segmentation/card-candidate-2026-05-09-05.png","category_code":"image-to-image","status_code":"active","family_id":"019e02fd-de04-7e21-9d59-b578c78f40ea","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Smart Segmentation API, Prompt-Guided Image Masks | Runflow","keywords":["smart segmentation","smart segmentation api","prompt guided segmentation","image segmentation api","segmentation mask api","object mask generation","image mask extraction","subject segmentation","part segmentation","computer vision api","image to image api","runflow segmentation"],"description":"Smart Segmentation API extracts prompt-selected image regions as masks for $0.12 per run through the Runflow API with simple image_url inputs."},"notable_features":["prompt-guided segmentation","image masks","part selection","fixed per-image pricing","multi-region failover"],"content":"## Overview\n\nSmart Segmentation extracts a prompt-selected subject or region from an input image and returns a mask through the standard Runflow output contract. Send an image URL and a concrete prompt such as \"left shoe\", \"mug handle\", or \"character head\" to target the region you need.\n\n## Key capabilities\n\n- **$0.12 per successful image**, fixed per-run pricing for prompt-guided segmentation masks.\n- **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.\n- **Prompt-guided selection**, useful when a scene contains multiple objects and you need a specific part instead of the whole foreground.\n- **Simple API shape**, production calls use `image_url` and `prompt`; internal filename handling is inferred automatically from the URL.\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Input | Image URL plus text prompt |\n| Output | Image mask in `outputs[]` |\n| Category | Image to image |\n| Pricing | $0.12 per successful run |\n","pricing_note":null,"created_at":"2026-05-07T15:10:52.741772Z","updated_at":"2026-05-14T20:00:50.709822Z"},{"id":"019dfa06-5234-73b3-b49b-2143c81f1a6f","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/background-replace","name":"Background Replace","description":"Swap the background of any product photo for a new scene defined by a reference image and a short prompt. The model preserves the foreground subject while matching camera angle and lighting to the new background.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/background-replace/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":null,"max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":null,"content":null,"pricing_note":null,"created_at":"2026-05-05T21:23:31.510947Z","updated_at":"2026-05-06T07:36:02.108800Z"},{"id":"019df9c6-a82a-7240-bda9-3cd66885349b","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/reference-inpaint","name":"Reference Inpaint","description":"Inpaint a region of a target photo using a reference image as the visual guide. Provide the target, a black-and-white mask of the area to fill, and a reference image. The model paints the masked region with content matching the reference.","version":"2.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/reference-inpaint/card-candidate-9.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Reference Inpaint API: paint masked regions from a reference image | Runflow","keywords":["reference inpaint","image inpainting","reference-guided inpaint","image edit","product placement","image to image","Runflow"],"description":"Fill a masked region of a photo using a reference image as the visual guide. Provide target, mask, and reference; the model paints the masked area to match. Per-image fixed pricing."},"notable_features":["Reference image guides the inpainted content","Pixel-perfect control via custom mask","Per-image billing"],"content":"## Overview\n\n**Reference Inpaint** fills a masked region of a target photo using the contents of a reference image as the visual guide. Provide the target, a black-and-white mask of the area to fill, and a reference image; the model paints the masked region with content matching the reference.\n\n## How it works\n\nSend a zip containing three images: a target photo, a black-and-white mask of the same dimensions (white = inpaint, black = keep), and a reference image whose visual content should fill the masked area. The model analyses the reference, blends its content into the masked region of the target, and returns the composited image at the original resolution.\n\n## Common use cases\n\n- Product placement: drop a product into a clean scene shot\n- Background or texture swap: replace a background or surface with a reference\n- Element insertion: add a piece of furniture, signage, or branding to a layout\n- Concept iteration: try different visual options without re-shooting\n","pricing_note":null,"created_at":"2026-05-05T20:13:59.210962Z","updated_at":"2026-05-24T15:01:57.846784Z"},{"id":"019df9bf-c137-7370-b0f6-830fabbdcb2f","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/product-isolation","name":"Product Isolation","description":"Isolate the main product from a busy scene onto a clean background, using an optional text prompt to disambiguate the subject. Built for studio-grade product photography at scale.","version":"2.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/product-isolation/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":null,"max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":null,"content":null,"pricing_note":null,"created_at":"2026-05-05T20:06:26.873220Z","updated_at":"2026-05-05T20:39:17.008810Z"},{"id":"019de9eb-c6b0-7a22-9904-549fa52aaf08","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/smart-resize","name":"Smart Resize","description":"Resize an image to a target aspect ratio + resolution (1K, 2K, 4K) without distortion or cropping. Uses generative reframing to recompose the subject into the new frame.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/smart-resize/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["Aspect-ratio + resolution targeting (1K / 2K / 4K)","Generative reframing — recomposes the subject, no letterboxing","Per-image billing"],"content":null,"pricing_note":null,"created_at":"2026-05-02T18:20:36.401402Z","updated_at":"2026-05-03T17:59:43.367591Z"},{"id":"019de9eb-a03c-7420-a919-3a4c4e762486","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/outpaint/aspect-ratio","name":"Outpaint (Aspect Ratio)","description":"Expand the canvas of an image to a target aspect ratio (e.g. 16:9, 1:1, 9:16). The model decides where to add content — no need to specify per-side expand percentages.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/outpaint/aspect-ratio/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["Aspect-ratio targeting (1:1, 4:3, 16:9, 9:16, 21:9, etc.)","Flux-fill backbone with multi-stage upscaling","Outputs at up to 4096px on the long side"],"content":null,"pricing_note":null,"created_at":"2026-05-02T18:20:26.561295Z","updated_at":"2026-05-03T17:59:42.505171Z"},{"id":"019dcfb2-e059-7082-9c3d-a1b2c1762e05","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/happy-horse/reference-to-video","name":"Happy Horse Reference-to-Video","description":"Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/happy-horse/reference-to-video/card-1.webp","category_code":"image-to-video","status_code":"active","family_id":"019dcfb3-4bf7-7dc1-a478-81d623e7f058","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Happy Horse Reference-to-Video API — Multi-Subject Scenes | Runflow","keywords":["happy horse","alibaba reference-to-video","multi-character video","reference image video","subject consistency","character video ai","video generation api","1080p video ai","ai video api","runflow"],"description":"Generate multi-character 1080p video from 1-9 reference images plus a prompt. Identity stays stable. Native audio + lip-sync. $0.14/s on Runflow."},"notable_features":["reference-to-video","1-9 references","1080p","identity preservation","native audio","lip-sync","multilingual"],"content":"## Overview\n\nHappy Horse Reference-to-Video composes 1080p multi-character scenes from **1-9 reference images plus a text prompt**. Reference images are addressable by index (`character1`, `character2`, …) so you can stage interactions, brand-consistent product placements, or multi-subject scenes with stable identity across the whole clip.\n\n## Key capabilities\n\n- **Up to 9 references**: each callable as `character1`-`character9` in your prompt — order matches your `image_urls` array\n- **Identity preservation**: subjects keep their reference appearance across motion and scene changes\n- **Native audio + lip-sync**: same audio engine as the rest of the family — multilingual and synchronized to motion\n- **Five aspect ratios**: 16:9, 9:16, 1:1, 4:3, 3:4\n- **3-15 second clips** at 720p or 1080p\n- **Strict reference quality**: each image must be ≥400px on the short side, ≤10MB, JPEG/JPG/PNG/WEBP — 720p+ recommended for clean identity\n\n## Family\n\nPart of the Happy Horse family — pair with the variants when you need a different starting modality:\n\n| Variant | Input | Use it for |\n|--------|-------|-----------|\n| Text-to-Video | text prompt | one-shot clips from a brief |\n| Image-to-Video | image + optional prompt | animating a still or hero shot |\n| Video Edit | source video + edit prompt | transforming an existing clip (style, scene swap) |\n| Reference-to-Video | text + 1-9 references | multi-character scenes, brand-consistent subjects |\n\n## Tech specs\n\n- **Resolutions**: 720p, 1080p\n- **Duration**: 3-15s\n- **References**: 1-9 images, ≥400px short side, ≤10MB each, callable as `character1`-`character9`\n- **Audio**: native, lip-synced, multilingual\n- **Aspect ratios**: 16:9, 9:16, 1:1, 4:3, 3:4\n- **Latency**: 90-240s typical for a 5s clip with multiple references\n- **Pricing**: $0.14/s at 720p, $0.28/s at 1080p — references don't change the price","pricing_note":null,"created_at":"2026-04-27T16:08:19.801859Z","updated_at":"2026-04-28T16:12:17.709298Z"},{"id":"019dcfb2-ceea-7532-b32c-2fdce5bee835","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/happy-horse/video-edit","name":"Happy Horse Video Edit","description":"HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/happy-horse/video-edit/card-1.webp","category_code":"video-to-video","status_code":"active","family_id":"019dcfb3-4bf7-7dc1-a478-81d623e7f058","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Happy Horse Video Edit API — Prompt-Based Video Editing | Runflow","keywords":["happy horse","alibaba video edit","video editing ai","prompt-based video editing","natural language video","video style transfer","video-to-video","reference image editing","ai video editor api","runflow"],"description":"Edit any video with natural-language prompts — recolor, restyle, or transform scenes. Up to 5 reference images. 1080p, $0.28/s. Production API on Runflow."},"notable_features":["video-to-video","prompt-based editing","1080p","reference images","audio control","global + local edits"],"content":"## Overview\n\nHappy Horse Video Edit transforms an existing clip with **natural-language instructions** — no masks, no keyframes, no manual rotoscoping. Describe the change you want (recolor a sky, swap a season, restyle the whole scene); attach up to 5 reference images for visual anchoring; get back a re-rendered clip that preserves the source's motion and aspect ratio.\n\n## Key capabilities\n\n- **Prompt-driven editing**: \"recolor the sky to a deep purple sunset,\" \"convert to film noir,\" \"add cherry blossoms throughout\" — global or local edits in one shot\n- **Reference image support**: include up to 5 reference images and call them as `@Image1`-`@Image5` in your prompt for visual fidelity\n- **Source-faithful**: aspect ratio is preserved; output duration matches input (longer-than-15s inputs truncate to the first 15s)\n- **Audio control**: keep, replace, or strip the source audio via the `audio_setting` parameter\n- **Wide input range**: MP4/MOV (H.264 recommended), 3-60s, ≤2160px long side, ≥320px short side, >8 fps, ≤100MB\n\n## Family\n\nPart of the Happy Horse family — pair with the variants when you need a different starting modality:\n\n| Variant | Input | Use it for |\n|--------|-------|-----------|\n| Text-to-Video | text prompt | one-shot clips from a brief |\n| Image-to-Video | image + optional prompt | animating a still or hero shot |\n| Video Edit | source video + edit prompt | transforming an existing clip (style, scene swap) |\n| Reference-to-Video | text + 1-9 references | multi-character scenes, brand-consistent subjects |\n\n## Tech specs\n\n- **Resolutions**: 720p, 1080p\n- **Source video**: MP4/MOV, 3-60s, ≤2160px long side, ≥320px short side, >8 fps, ≤100MB\n- **Output duration**: matches input, capped at 15s\n- **References**: up to 5 images, callable as `@Image1`-`@Image5` in the prompt\n- **Audio**: configurable via `audio_setting`\n- **Latency**: 90-240s typical (longer than text-to-video due to source decode + re-render)\n- **Pricing**: $0.28/s at 720p, $0.56/s at 1080p — input/output seconds are billed together, simple per-second billing","pricing_note":null,"created_at":"2026-04-27T16:08:15.339297Z","updated_at":"2026-04-28T16:12:17.529344Z"},{"id":"019dcfb2-be03-7170-98f3-1d275366df31","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/happy-horse/image-to-video","name":"Happy Horse Image-to-Video","description":"Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/happy-horse/image-to-video/card-1.webp","category_code":"image-to-video","status_code":"active","family_id":"019dcfb3-4bf7-7dc1-a478-81d623e7f058","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Happy Horse Image-to-Video API — 1080p with Lip-Sync | Runflow","keywords":["happy horse","alibaba video","image-to-video","image animation","lip-sync ai","multilingual lip-sync","video generation api","1080p video ai","ai video api","runflow"],"description":"Animate any image into 1080p video with synchronized native audio and multilingual lip-sync. 3-15s clips, $0.14/s. Production API on Runflow."},"notable_features":["image-to-video","1080p","native audio","lip-sync","multilingual","3-15s"],"content":"## Overview\n\nHappy Horse Image-to-Video animates a still image into 1080p video with **synchronized native audio and multilingual lip-sync**. Drop in a portrait, product shot, or scene; describe the motion (or skip it); get back a fully-scored clip with mouth movement that actually tracks the audio.\n\n## Key capabilities\n\n- **Native audio + lip-sync**: ambient sound, music, dialogue all generated in sync — and if a face is in frame, lips track the speech in 30+ languages\n- **Optional prompt**: leave it empty for a natural extension of the image, or steer the motion explicitly\n- **Aspect-ratio preservation**: output keeps the source image's ratio (constrained between 1:2.5 and 2.5:1)\n- **3-15 second clips** at 720p or 1080p\n- **Strict input requirements**: image must be ≥300px on the short side, ≤10MB, JPEG/PNG/WEBP/BMP\n\n## Family\n\nPart of the Happy Horse family — pair with the variants when you need a different starting modality:\n\n| Variant | Input | Use it for |\n|--------|-------|-----------|\n| Text-to-Video | text prompt | one-shot clips from a brief |\n| Image-to-Video | image + optional prompt | animating a still or hero shot |\n| Video Edit | source video + edit prompt | transforming an existing clip (style, scene swap) |\n| Reference-to-Video | text + 1-9 references | multi-character scenes, brand-consistent subjects |\n\n## Tech specs\n\n- **Resolutions**: 720p, 1080p\n- **Duration**: 3-15s\n- **Image limits**: ≥300px short side, ≤10MB, JPEG/PNG/WEBP/BMP\n- **Audio**: native, lip-synced, multilingual\n- **Latency**: 60-180s typical for a 5s clip\n- **Pricing**: $0.14/s at 720p, $0.28/s at 1080p — simple per-second billing, no minimums","pricing_note":null,"created_at":"2026-04-27T16:08:11.013872Z","updated_at":"2026-04-28T16:12:17.156193Z"},{"id":"019dcfb2-9e52-71e3-8e81-7d645d2c645a","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/happy-horse/text-to-video","name":"Happy Horse Text-to-Video","description":"Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/happy-horse/text-to-video/card-1.webp","category_code":"text-to-video","status_code":"active","family_id":"019dcfb3-4bf7-7dc1-a478-81d623e7f058","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Happy Horse Text-to-Video API — 1080p with Native Audio | Runflow","keywords":["happy horse","alibaba video","text-to-video","video generation api","native audio video","1080p video ai","16:9 9:16 video","synchronized audio","ai video api","runflow"],"description":"Generate 1080p video with synchronized native audio from a single text prompt. 5 aspect ratios, 3-15s clips, $0.14/s. Production API on Runflow."},"notable_features":["text-to-video","1080p","native audio","multilingual","5 aspect ratios","3-15s"],"content":"## Overview\n\nHappy Horse Text-to-Video is Alibaba's flagship 1080p video generator with **synchronized native audio** built in — no separate audio model, no lip-sync rig, no post-production. Send a single prompt; get a fully-scored clip back.\n\n## Key capabilities\n\n- **Native audio**: ambient sound, music, voice, foley — generated in lock-step with the visuals so they actually match (no overlay tricks)\n- **Multilingual**: prompts and any embedded dialogue work across major languages\n- **Five aspect ratios**: 16:9, 9:16, 1:1, 4:3, 3:4 — covers landscape ads, vertical short-form, square social, and portrait formats from one endpoint\n- **3-15 second clips** at 720p or 1080p\n- **Cinematic motion**: handles complex camera moves (dolly, push-in, aerial), shallow DOF, golden-hour lighting prompts well\n\n## Family\n\nPart of the Happy Horse family — pair with the variants when you need a different starting modality:\n\n| Variant | Input | Use it for |\n|--------|-------|-----------|\n| Text-to-Video | text prompt | one-shot clips from a brief |\n| Image-to-Video | image + optional prompt | animating a still or hero shot |\n| Video Edit | source video + edit prompt | transforming an existing clip (style, scene swap) |\n| Reference-to-Video | text + 1-9 references | multi-character scenes, brand-consistent subjects |\n\n## Tech specs\n\n- **Resolutions**: 720p, 1080p\n- **Duration**: 3-15s\n- **Audio**: native, in-sync, prompt-controlled\n- **Latency**: 60-180s typical for a 5s clip; queue depth varies during peak hours\n- **Pricing**: $0.14/s at 720p, $0.28/s at 1080p — simple per-second billing, no minimums","pricing_note":null,"created_at":"2026-04-27T16:08:02.901498Z","updated_at":"2026-04-28T16:12:16.960232Z"},{"id":"019dc580-b6aa-7012-899b-b5e42ee1499f","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/object-removal","name":"Object Removal","description":"Remove an unwanted object or region from a photo. Mark the area to remove with a black-and-white mask. The model rebuilds the background using surrounding context.","version":"4.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/object-removal/card-candidate-11.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Object Removal API: mask-driven photo cleanup | Runflow","keywords":["object removal","image inpainting","remove object","photo cleanup","mask-driven inpaint","image to image","Runflow"],"description":"Remove any object from a photo by providing a black-and-white mask. The background rebuilds to match the surrounding scene. Per-image fixed pricing."},"notable_features":["Pixel-perfect control via custom mask","Clean fills that match surrounding pixels","Per-image billing"],"content":"## Overview\n\n**Object Removal** clears a region of an image and rebuilds the background to match the rest of the scene. You control exactly what gets removed by providing a black-and-white mask.\n\n## How it works\n\nSend the source photo and a paired black-and-white mask of the same dimensions. White pixels mark what to remove, black pixels mark what to keep, soft greys produce partial blending. The model rebuilds the masked area using surrounding context and returns the cleaned image at the original resolution.\n\n## Common use cases\n\n- Removing props, watermarks, or distractions from product shots\n- Cleaning up backgrounds before composition\n- Editing portraits to remove clutter\n- Marketing asset prep at scale\n","pricing_note":null,"created_at":"2026-04-25T16:37:20.170676Z","updated_at":"2026-05-24T15:01:36.185148Z"},{"id":"019dc580-aa02-7f62-b71b-d58b59e729a3","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/skin-fix","name":"Skin Fix","description":"Cleanup pass for portrait photography. Smoothes skin texture, fixes blemishes, preserves natural detail.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/skin-fix/card-candidate-2.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Skin Fix API — natural skin retouch for portraits | Runflow","keywords":["skin fix","skin retouch","portrait retouching","face inpaint","beauty retouch","AI portrait","image to image","Runflow"],"description":"AI portrait skin cleanup. Smooths blemishes; preserves texture and detail. No customer-facing knobs — tuned for natural results. Per-image fixed pricing."},"notable_features":["Inpainting-based — does not blur the whole face","Tuned for natural skin texture (no customer-facing knobs)","Per-image billing"],"content":"## Overview\n\n**Skin Fix** is a portrait-cleanup pass. Smooths skin texture, fixes blemishes,\nand preserves natural detail. Tuned for natural results — no plastic look.\n\n## How it works\n\nSend any portrait URL. A face-aware inpainting + upscaling pipeline targets\nskin specifically (does not blur the whole face).\n\n## Common use cases\n\n- Headshot prep at scale (LinkedIn, agency rosters)\n- E-commerce model shots with consistent skin quality\n- Volume retouching for catalog photography\n\n## API call shape\n\n```json\nPOST /v1/models/runflow/skin-fix/runs\n{ \"image_url\": \"https://…/portrait.jpg\" }\n```","pricing_note":null,"created_at":"2026-04-25T16:37:16.930525Z","updated_at":"2026-04-28T16:13:51.827885Z"},{"id":"019dc580-992f-7d53-b3bf-20469428dd22","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/eye-color","name":"Eye Color","description":"Recolor the irises in a portrait. The customer describes the target eye color (e.g. \"blue\", \"emerald green\", \"amber\") — that drives the inpaint guidance. Optional RGB lets you tint the overlay precisely.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/eye-color/card-candidate-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Eye Color API — recolor irises in portraits | Runflow","keywords":["eye color change","iris recolor","portrait edit","face inpaint","cosmetics visualization","AI portrait","image to image","Runflow"],"description":"AI-driven iris recoloring for portraits. RGB-driven; face-aware inpainting + upscaling preserves natural detail. Per-image fixed pricing."},"notable_features":["Customer-described target colour drives the inpaint","Inpainting + upscaling preserves face detail","Per-image billing"],"content":"## Overview\n\n**Eye Color** recolors the irises in a portrait. Describe the target eye color in plain language (\"blue\", \"emerald green\", \"amber\", \"deep brown\") and the pipeline performs a face-aware inpaint + upscale that preserves natural eye texture, eyelash detail, and surrounding skin. RGB channel values let you tint the colour overlay precisely.\n\n## How it works\n\nProvide an image URL, the inner filename in the bundle (`file_input`), the customer-facing target eye colour (`eye_color`), and three RGB channel values. A face-detection step locates the eyes; an inpainting + upscaling pass recolours the irises using `eye_color` to drive the guidance prompt, while preserving anatomical detail.\n\n## Common use cases\n\n- Portrait retouching at scale\n- Cosmetic-product visualization (lens campaigns)\n- Stylized portrait variations\n\n## API call shape\n\n```json\nPOST /v1/models/runflow/eye-color/runs\n{\n  \"image_url\": \"https://…/portrait-bundle.zip\",\n  \"file_input\": \"portrait.png\",\n  \"eye_color\": \"emerald green\",\n  \"color_red\": 40, \"color_green\": 160, \"color_blue\": 100\n}\n```","pricing_note":null,"created_at":"2026-04-25T16:37:12.623820Z","updated_at":"2026-05-03T12:00:01.349674Z"},{"id":"019dc580-86cd-7a23-bf25-c4c177adaf73","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/outpaint","name":"Outpaint (Expand)","description":"Expand the canvas of an image with AI-generated content that matches the existing scene. Specify percent expand on each side — required so the customer is intentional.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/outpaint/card-candidate-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Outpaint (Expand) API — Flux-fill canvas extension | Runflow","keywords":["outpaint","outpainting","image expand","canvas expand","aspect ratio change","Flux fill","image extension","AI image editing","Runflow"],"description":"Expand the canvas of an image with AI-generated continuation. Per-side controls; Flux-fill backbone; outputs to 4096px. Per-image fixed pricing."},"notable_features":["Per-side expand controls (top / bottom / left / right %, all required)","Flux-fill backbone with multi-stage upscaling","Outputs at up to 4096px on the long side"],"content":"## Overview\n\n**Outpaint (Expand)** grows the canvas of an image with AI-generated content\nthat matches the existing scene. Specify how many percent to expand on each\nof the four edges; the pipeline runs Flux-fill plus multi-stage upscaling and\nreturns a coherent result up to 4096px on the long side.\n\n## How it works\n\nProvide an image URL and four expand-percent values (0–80 each). The pipeline\ngenerates plausible scene continuations, multiplies through Flux fill, then\napplies a tea-cached upscaler pass for sharpness.\n\n## Common use cases\n\n- Aspect-ratio adaptation — turn 4:3 into 16:9 without cropping the subject\n- Scene extension — add headroom or footroom for typography\n- Reposition for layouts — extend the canvas instead of cropping\n\n## API call shape\n\n```json\nPOST /v1/models/runflow/outpaint/runs\n{ \"image_url\": \"https://…/photo.jpg\",\n  \"expand_top\": 30, \"expand_bottom\": 20,\n  \"expand_left\": 20, \"expand_right\": 20 }\n```","pricing_note":null,"created_at":"2026-04-25T16:37:07.917685Z","updated_at":"2026-04-28T16:13:52.548914Z"},{"id":"019dc580-7674-7d52-bac0-b93afff89721","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/background-color","name":"Background Color","description":"Replace the background of a portrait or product shot with a flat color. Pick any RGB value; shading_percent baked at 30% for soft falloff.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/background-color/card-candidate-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019dc580-2799-7992-847d-62142c7b8f9c","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Background Color API — flat-color background replacement | Runflow","keywords":["background color","background replacement","background change","flat background","product photography","studio background","inpainting","image to image","Runflow"],"description":"Replace any background with a flat RGB color. Inpainting preserves subject detail; shading falloff keeps it photographic. Per-image fixed pricing."},"notable_features":["Pick any RGB color (required — no presumed default)","Inpainting preserves subject detail","Per-image billing — only successful items are charged"],"content":"## Overview\n\n**Background Color** replaces the background of a portrait or product shot\nwith a flat color of your choice. Fully controllable via three RGB channel\ninputs (0–255 each); a fixed shading falloff keeps the result soft and\nphotographic.\n\n## How it works\n\nProvide an image URL plus the three RGB channel values. The pipeline detects\nthe subject, replaces the background with your color, applies a 30% gradient\nfalloff, and returns the result at the original resolution.\n\n## Common use cases\n\n- Catalog pages — uniform backgrounds across thousands of products\n- Branded marketing — match exact corporate colors\n- Studio standardisation — pure white, soft grey, or vivid hues without re-shooting\n\n## API call shape\n\n```json\nPOST /v1/models/runflow/background-color/runs\n{ \"image_url\": \"https://…/portrait.jpg\",\n  \"color_red\": 240, \"color_green\": 240, \"color_blue\": 240 }\n```","pricing_note":null,"created_at":"2026-04-25T16:37:03.734318Z","updated_at":"2026-04-28T16:13:52.193134Z"},{"id":"019db17f-e186-7870-8000-c456a9057d84","model_creator_id":"019d4f45-0dda-7773-8854-216f35470402","slug":"openai/gpt-image-2/edit","name":"GPT Image 2 Edit","description":"GPT Image 2.0, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/openai/gpt-image-2/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-8460-7673-b345-92045c676346","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"GPT Image 2 Edit API — OpenAI Image Editing | Runflow","keywords":["gpt image 2 edit","openai image edit api","gpt-image-2 edit","openai image editor","ai image editing api","inpainting api","gpt image inpainting","openai edit api","typography editing","runflow image edit","openai api","ai mask editor"],"description":"GPT Image 2 Edit API. Fine-grained image editing with OpenAI's latest. Multi-reference, mask-based inpainting. $0.009–$0.133/image. Automatic failover."},"notable_features":["image-to-image","editing","openai","gpt-image","inpainting"],"content":"## Overview\n\nGPT Image 2 Edit by OpenAI applies fine-grained, detail-preserving edits to existing images from a natural-language prompt. Best-in-class for typography edits, compositional changes, and reference-guided transformations.\n\n## Key capabilities\n\n- **$0.009–$0.133 per image** (low/medium/high quality) — usage-based.\n- **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.\n- **Multi-image reference**, provide up to several reference images for composition-aware editing.\n- **Optional mask**, target a specific region of the image with `mask_url` for precise inpainting.\n\n## GPT Image family\n\n| Model | Details |\n|---|---|\n| **GPT Image 2 Edit** (this model) | Image editing, latest generation |\n| **GPT Image 2** | Text-to-image sibling |\n| **GPT Image 1.5 Edit** | Previous generation editor |\n| **GPT Image 1.5** | Previous generation text-to-image |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Quality tiers | low, medium, high (default) |\n| Output formats | png, jpeg, webp |\n| Inputs | prompt, image_urls (required), optional mask_url |\n| Pricing | $0.009 (low), $0.034 (medium), $0.133 (high) per image |","pricing_note":null,"created_at":"2026-04-21T19:24:01.287333Z","updated_at":"2026-04-21T20:00:29.592338Z"},{"id":"019db17f-d6a1-7031-97ad-b63d30379956","model_creator_id":"019d4f45-0dda-7773-8854-216f35470402","slug":"openai/gpt-image-2","name":"GPT Image 2","description":"GPT Image 2.0, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/openai/gpt-image-2/card-1.webp","category_code":"text-to-image","status_code":"active","family_id":"019d5da6-8460-7673-b345-92045c676346","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"GPT Image 2 API — OpenAI's Latest Text-to-Image | Runflow","keywords":["gpt image 2","gpt image 2 api","openai image api","openai text to image","gpt-image-2","ai image generator","text to image api","openai gpt image","gpt image pricing","openai api","runflow gpt image","typography ai image"],"description":"GPT Image 2 API by OpenAI. State-of-the-art text-to-image with exceptional typography. $0.009–$0.133/image by quality tier. Automatic failover."},"notable_features":["text-to-image","typography","openai","gpt-image"],"content":"## Overview\n\nGPT Image 2 by OpenAI is a text-to-image model with exceptional typography rendering, strong prompt adherence, and fine-grained control over composition, lighting, and detail.\n\n## Key capabilities\n\n- **$0.009–$0.133 per image** (low/medium/high quality) — usage-based, pay only for what you generate.\n- **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.\n- **Best-in-class text rendering**, readable typography, accurate signage, and controlled layouts.\n- **Up to 10 images per request**, set the `num_images` parameter for batch generation.\n\n## GPT Image family\n\n| Model | Details |\n|---|---|\n| **GPT Image 2** (this model) | Latest generation, text-to-image, improved typography and detail |\n| **GPT Image 2 Edit** | Same model for image editing — provide reference image(s) and edit prompt |\n| **GPT Image 1.5** | Previous generation, text-to-image |\n| **GPT Image 1.5 Edit** | Previous generation, image editing |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Quality tiers | low, medium, high (default) |\n| Output formats | png, jpeg, webp |\n| Max images per request | 10 |\n| Pricing | $0.009 (low), $0.034 (medium), $0.133 (high) per image |","pricing_note":null,"created_at":"2026-04-21T19:23:58.500669Z","updated_at":"2026-04-21T20:00:29.407676Z"},{"id":"019db0d0-d3a0-7916-92ed-a06f7bd5201f","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/tag-removal","name":"Tag Removal","description":"Remove price tags, stickers, and labels from product images while preserving the underlying material and lighting. Ideal for re-listing inventory or cleaning up user-submitted photography.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/tag-removal/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["Single-filter preset of the dyver-removal workflow","Batch up to 100 images via POST /v1/models/{owner}/{slug}/batches","Per-image billing — only successful items are charged"],"content":null,"pricing_note":null,"created_at":"2026-04-21T16:12:48.926021Z","updated_at":"2026-04-21T22:16:49.648972Z"},{"id":"019db0d0-d3a0-76fe-8ff9-7a3510110576","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/model-removal","name":"Model Removal","description":"Remove the human model from a garment or apparel photo and recover a clean flat-lay or ghost-mannequin view. Designed for fashion catalogs and PDP hero shots.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/model-removal/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["Single-filter preset of the dyver-removal workflow","Batch up to 100 images via POST /v1/models/{owner}/{slug}/batches","Per-image billing — only successful items are charged"],"content":null,"pricing_note":null,"created_at":"2026-04-21T16:12:48.926021Z","updated_at":"2026-04-21T22:16:50.740904Z"},{"id":"019db0d0-d3a0-75a3-8a42-826e4e6feaf7","model_creator_id":"019da096-7891-7087-864c-9edd02991a35","slug":"runflow/background-removal","name":"Background Removal","description":"Remove the background from an image and return a clean cutout with a transparent alpha channel. Built for e-commerce product shots, portraits, and batch cleanup pipelines.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/runflow/background-removal/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019da096-7891-7137-96e7-76ca38a58d11","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":null,"notable_features":["Single-filter preset of the dyver-removal workflow","Batch up to 100 images via POST /v1/models/{owner}/{slug}/batches","Per-image billing — only successful items are charged"],"content":null,"pricing_note":null,"created_at":"2026-04-21T16:12:48.926021Z","updated_at":"2026-04-21T22:16:48.632351Z"},{"id":"019daefc-e551-79e2-bdb5-2f2a5d822b58","model_creator_id":"019d52a5-9123-7c91-bf46-a441863ed0c1","slug":"heygen/v3/video-agent","name":"HeyGen Video Agent V3","description":"Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/heygen/v3/video-agent/card-1.webp","category_code":"text-to-video","status_code":"active","family_id":"019d5da6-d823-7052-9824-fc9a1f1756ef","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"HeyGen Video Agent V3 API — Prompt-to-Video at $0.034/sec | Runflow","keywords":["heygen v3 api","heygen video agent","ai video from prompt","text to video api","prompt to video ai","heygen api pricing","ai avatar video","video agent api","heygen video generation","runflow api","heygen alternative","heygen v3 video agent"],"description":"HeyGen Video Agent V3 API. Generate full videos from a single prompt — agent handles avatar, script, and production. $0.034/second, automatic failover."},"notable_features":["text-to-video","avatar","agent","one-shot"],"content":"## Overview\n\nHeyGen Video Agent V3 by HeyGen generates complete videos from a single natural-language prompt. The agent handles avatar selection, script writing, scene composition, and production automatically — describe the video you want and it produces a finished MP4.\n\n## Key capabilities\n\n- **$0.034 per second of generated video**, simple usage-based pricing (~29 seconds per $1).\n- **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.\n- **Agent-driven production**, no separate script writing or avatar selection needed.\n- **Optional asset grounding**, pass up to 20 reference files (images, videos, audio, PDFs) to shape the output.\n\n## HeyGen family\n\n| Model | Details |\n|---|---|\n| **HeyGen Video Agent V3** (this model) | Single-prompt agent, selects avatar/script/voice automatically |\n| **HeyGen Video Agent V2** | Earlier agent generation with prompt + config |\n| **HeyGen Avatar4** | Image-to-video with explicit avatar selection |\n| **HeyGen V2 Translate** | Multilingual dubbing and lip-sync |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Architecture | Agentic video generation |\n| Input | Natural language prompt (up to 10,000 characters) |\n| Output | MP4 video (landscape or portrait) |\n| Max input files | 20 (images, videos, audio, PDFs) |\n| Pricing | $0.034 / second of generated video |","pricing_note":null,"created_at":"2026-04-21T07:41:42.613539Z","updated_at":"2026-04-21T20:00:37.224673Z"},{"id":"019d6e52-a11b-7d32-be20-14fe317d1661","model_creator_id":"019d40e6-d4bd-75a3-b0fd-28a2e2d6a490","slug":"black-forest-labs/flux-2-klein-9b/edit","name":"FLUX.2 [klein] 9B — Edit","description":"Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/black-forest-labs/flux-2-klein-9b/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d6e68-bf59-77e2-bd99-643b080d8221","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"FLUX.2 [klein] 9B — Edit API — Image To Image | Runflow","keywords":["FLUX.2 [klein] 9B — Edit API","image to image API"],"description":"Run FLUX.2 [klein] 9B — Edit on Runflow. Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control."},"notable_features":null,"content":"## Overview\n\nFLUX.2 [klein] 9B Edit enables image-to-image editing with natural language instructions. Pass up to 4 reference images alongside your text prompt for guided editing, style transfer, or composition tasks.\n\n## Key Features\n\n- **Multi-image editing** — up to 4 reference images\n- **Natural language control** — describe edits in plain text\n- **Hex color control** — precise color specification\n- **Sub-second inference** — distilled to 4 steps\n\n## When to Use\n\nUse for image editing, style transfer, outfit changes, face swaps, and compositing tasks where you need to reference existing images.","pricing_note":null,"created_at":"2026-04-08T18:20:02.204413Z","updated_at":"2026-04-08T18:44:15.147514Z"},{"id":"019d6e52-8517-7450-9c67-41f5fd183bef","model_creator_id":"019d40e6-d4bd-75a3-b0fd-28a2e2d6a490","slug":"black-forest-labs/flux-2-klein-9b","name":"FLUX.2 [klein] 9B","description":"Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/black-forest-labs/flux-2-klein-9b/card-1.webp","category_code":"text-to-image","status_code":"active","family_id":"019d6e68-bf59-77e2-bd99-643b080d8221","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"FLUX.2 [klein] 9B API — Text To Image | Runflow","keywords":["FLUX.2 [klein] 9B API","text to image API"],"description":"Run FLUX.2 [klein] 9B on Runflow. Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities."},"notable_features":null,"content":"## Overview\n\nFLUX.2 [klein] 9B is a 9-billion parameter image generation model from Black Forest Labs. Distilled to just 4 inference steps for sub-second generation. Uses an 8B Qwen3 text embedder and supports up to 4 megapixel output resolution.\n\n## Key Features\n\n- **Sub-second inference** — distilled to 4 steps\n- **Higher quality than 4B** — 9B parameters for richer detail and diversity\n- **Text rendering** — strong text-in-image capabilities from FLUX.2\n- **Up to 4MP resolution** — dimensions must be multiples of 16\n\n## When to Use\n\nChoose the 9B variant over 4B when output quality and diversity matter more than speed. Note: this model uses the FLUX Non-Commercial License.","pricing_note":null,"created_at":"2026-04-08T18:19:55.032995Z","updated_at":"2026-04-08T18:44:14.777282Z"},{"id":"019d644a-fc73-7c43-ac64-c57c02a47e15","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/wan/v2.7/image-to-video","name":"Wan 2.7 — Image to Video","description":"Wan 2.7 delivers enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/wan/v2.7/image-to-video/card-1.webp","category_code":"image-to-video","status_code":"active","family_id":"019d6e68-be1f-7d43-aa69-1c472c6b12d3","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Wan 2.7 — Image to Video API — Image To Video | Runflow","keywords":["Wan 2.7 — Image to Video API","image to video API"],"description":"Run Wan 2.7 — Image to Video on Runflow. Wan 2.7 delivers enhanced motion smoothness, superior scene fidelity, and greater visual coherence."},"notable_features":null,"content":"## Overview\n\nWan 2.7 Image-to-Video animates images with enhanced motion smoothness and scene fidelity. Supports first-and-last-frame control, audio-driven generation, and video continuation.\n\n## Key Features\n\n- **Multi-modal input** — image, video continuation, or audio-driven\n- **End-frame control** — specify the last frame\n- **1080p output** — professional resolution\n- **Up to 15 seconds** — long clip support\n\n## When to Use\n\nVersatile I2V model — use for image animation, video continuation, or audio-driven talking head generation.","pricing_note":null,"created_at":"2026-04-06T19:35:29.140318Z","updated_at":"2026-04-08T18:44:13.787868Z"},{"id":"019d6449-0217-7791-9faa-642b97010339","model_creator_id":"019d6447-6f41-7d10-92f9-4acd7fb2967a","slug":"reve/edit","name":"Reve Edit","description":"Reve's edit model lets you upload an existing image and then transform it via a text prompt.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/reve/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d6e68-bffb-7a43-8450-2a0a265fa9e9","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Reve Edit API — Image To Image | Runflow","keywords":["Reve Edit API","Reve Edit pricing","image to image API"],"description":"Run Reve Edit on Runflow with one API call. Reve's edit model lets you upload an existing image and then transform it via a text prompt."},"notable_features":null,"content":"## Overview\n\nReve is ranked #1 in the Artificial Analysis image editing arena (ELO 1283). It delivers exceptional editing quality for natural language-driven image modifications.\n\n## Key Features\n\n- **#1 editing model** — ELO 1283, highest in the arena\n- **Natural language editing** — describe changes in plain text\n- **High fidelity** — preserves unedited regions accurately\n- **Commercial license** — fully commercial use\n\n## When to Use\n\nThe best choice for image editing quality. Use when edit accuracy and preservation of original content matter most.","pricing_note":null,"created_at":"2026-04-06T19:33:19.511720Z","updated_at":"2026-04-08T18:44:15.450054Z"},{"id":"019d6448-d988-7770-bcb0-1286a73abf4a","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/wan/v2.7/text-to-video","name":"Wan 2.7 Text to Video","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/wan/v2.7/text-to-video/card-1.webp","category_code":"text-to-video","status_code":"active","family_id":"019d6e68-be1f-7d43-aa69-1c472c6b12d3","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Wan 2.7 Text to Video API — Text To Video | Runflow","keywords":["Wan 2.7 Text to Video API","Wan 2.7 Text to Video pricing","text to video API"],"description":"Run Wan 2.7 Text to Video on Runflow with one API call. Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence."},"notable_features":null,"content":"## Overview\n\nWan 2.7 is Alibaba's latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence. Supports up to 1080p resolution and 15-second clips.\n\n## Key Features\n\n- **1080p output** — professional resolution\n- **Up to 15 seconds** — longer clips than most models\n- **Audio support** — driving audio for lipsync\n- **Prompt expansion** — intelligent prompt rewriting\n\n## When to Use\n\nChoose Wan 2.7 for high-quality video generation with the flexibility of long clips and audio control.","pricing_note":null,"created_at":"2026-04-06T19:33:09.130845Z","updated_at":"2026-04-08T18:44:13.471092Z"},{"id":"019d6447-ec4b-7783-a93c-b1993d396050","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/wan/v2.7/pro/edit","name":"Wan 2.7 Pro Edit","description":"Edit and transform images using text instructions with the WAN 2.7 Pro model for precise, professional-grade image modifications.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/wan/v2.7/pro/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d6e68-be1f-7d43-aa69-1c472c6b12d3","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Wan 2.7 Pro Edit API — Image To Image | Runflow","keywords":["Wan 2.7 Pro Edit API","Wan 2.7 Pro Edit pricing","image to image API"],"description":"Run Wan 2.7 Pro Edit on Runflow with one API call. Edit and transform images using text instructions with the WAN 2.7 Pro model for precise, professional-grade image modifications."},"notable_features":null,"content":"## Overview\n\nWan 2.7 Pro Edit enables video editing and style transfer using natural language prompts. Edit existing videos by describing the changes you want, with optional reference images for style guidance.\n\n## Key Features\n\n- **Video editing** — modify existing videos with text prompts\n- **Style transfer** — apply reference image styles\n- **Audio preservation** — keep original audio or regenerate\n- **1080p output** — professional resolution\n\n## When to Use\n\nUse for video style transfer, editing, and re-stylization tasks where you want to transform existing footage.","pricing_note":null,"created_at":"2026-04-06T19:32:08.396132Z","updated_at":"2026-04-08T18:44:14.091507Z"},{"id":"019d52d6-2960-7850-a499-f015ce6e211b","model_creator_id":"019d4f45-095d-7f91-9299-dba1feafad84","slug":"kuaishou/kling-video/v3/pro/image-to-video","name":"Kling v3 Pro — Image to Video","description":"Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/kuaishou/kling-video/v3/pro/image-to-video/card-1.webp","category_code":"image-to-video","status_code":"active","family_id":"019d5da6-cd16-7a60-8c2e-17f36674ba73","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Kling Video v3 Image to Video [Pro] API — Video Generation Model | Runflow","keywords":["Kling Video v3 Image to Video [Pro] API","Kling Video v3 Image to Video [Pro] pricing","Kuaishou Kling Video v3 Image to Video [Pro]","image-to-video API","best image-to-video model"],"description":"Access Kuaishou's Kling Video v3 Image to Video [Pro] for image animation on Runflow. Production-ready API with Sentinel scoring. $0.14/seconds."},"notable_features":["image-to-video"],"content":"## Overview\n\nKling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support. Users can expect high-quality animation preserving source detail in production. Built for production workloads, from prototyping to millions of requests.","pricing_note":null,"created_at":"2026-04-03T10:14:20.256754Z","updated_at":"2026-04-05T21:08:19.516941Z"},{"id":"019d52d5-3714-7861-8f45-a250fa005c20","model_creator_id":"019d4f45-095d-7f91-9299-dba1feafad84","slug":"kuaishou/kling-video/v3/pro/text-to-video","name":"Kling v3 Pro — Text to Video","description":"Kling 3.0 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/kuaishou/kling-video/v3/pro/text-to-video/card-1.webp","category_code":"text-to-video","status_code":"active","family_id":"019d5da6-cd16-7a60-8c2e-17f36674ba73","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Kling Video v3 Text to Video [Pro] API — Video Generation Model | Runflow","usage":{"replicate_runs":201304},"keywords":["Kling Video v3 Text to Video [Pro] API","Kling Video v3 Text to Video [Pro] pricing","Kuaishou Kling Video v3 Text to Video [Pro]","text-to-video API","best text-to-video model"],"description":"Run Kling Video v3 Text to Video [Pro] via Runflow's API. Multi-region failover and Sentinel quality scoring. No GPU management."},"notable_features":["text-to-video"],"content":"## Overview\n\nKling 3.0 Pro by Kuaishou delivers cinematic video generation with native audio and industry-leading motion quality, particularly excelling in dynamic scenes with complex subject interactions. Its 3D VAE architecture produces temporally consistent frames with fluid motion that avoids the stiffness common in competing video models. Runflow integrates Kling 3.0 Pro with automatic failover to Replicate and Sentinel-powered quality evaluation across cinematic, motion, and audio dimensions — making it a reliable backbone for automated video production workflows.","pricing_note":null,"created_at":"2026-04-03T10:13:18.228711Z","updated_at":"2026-04-06T18:22:00.356405Z"},{"id":"019d52ce-16ad-7163-9013-92d9ef459aa5","model_creator_id":"019d4f45-0851-79e3-97bf-0d06bc45b917","slug":"ideogram/v3","name":"Ideogram v3","description":"Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/ideogram/v3/card-1.webp","category_code":"text-to-image","status_code":"active","family_id":"019d5da6-a2cc-7460-8daf-b51203b3ef77","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Ideogram Text to Image API — Image Generation Model | Runflow","usage":{"replicate_runs":8374973},"keywords":["Ideogram Text to Image API","Ideogram Text to Image pricing","Ideogram Ideogram Text to Image","text-to-image API","best text-to-image model"],"description":"Run Ideogram Text to Image via Runflow's API. Multi-region failover and Sentinel quality scoring. No GPU management."},"notable_features":["realism","typography"],"content":"## Overview\n\nIdeogram v3 sets the industry benchmark for text rendering within AI-generated images, producing legible, stylistically integrated typography that other models consistently fail to achieve. With turbo, balanced, and quality generation tiers, it adapts to workflows ranging from rapid social media asset creation to high-fidelity marketing collateral. Runflow exposes all three Ideogram tiers through a single API, with Sentinel scoring that specifically evaluates text legibility and integration — making it the definitive choice for any use case where words in images must be pixel-perfect.","pricing_note":null,"created_at":"2026-04-03T10:05:31.181525Z","updated_at":"2026-04-06T18:21:59.914565Z"},{"id":"019d52cc-0f71-74b0-ba9e-c7b020ba2708","model_creator_id":"019d40e6-d656-7250-8146-1707e98a6c74","slug":"google/gemini-tts","name":"Gemini TTS","description":"Google's Gemini TTS converts text to realistic audio. 30 voice presets, multi-speaker synthesis (up to 10 speakers), 24+ languages, and inline style markers for expressive control.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/google/gemini-tts/card-1.webp","category_code":"text-to-audio","status_code":"active","family_id":"019d6e68-c094-7401-8afc-f2293881610b","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Gemini TTS API | Runflow","keywords":["Gemini TTS API","Gemini TTS pricing","Google Gemini TTS","text-to-audio API","best text-to-audio model"],"description":"Access Google's Gemini TTS on Runflow. Production-ready API with Sentinel scoring."},"notable_features":null,"content":"## Overview\n\nGoogle's Gemini TTS converts text to realistic audio. 30 voice presets, multi-speaker synthesis (up to 10 speakers), 24+ languages, and inline style markers for expressive control.","pricing_note":null,"created_at":"2026-04-03T10:03:18.258434Z","updated_at":"2026-04-08T18:44:15.773438Z"},{"id":"019d52cb-dab6-7962-b6c9-1a357f3b0dff","model_creator_id":"019d40e6-d656-7250-8146-1707e98a6c74","slug":"google/nano-banana-2/edit","name":"Nano Banana 2 — Edit","description":"Nano Banana 2 is Google's new state-of-the-art image generation and editing model","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/google/nano-banana-2/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-97d1-77f0-95e4-c8c99fa95013","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Nano Banana 2 API — Image Editing Model | Runflow","keywords":["Nano Banana 2 API","Nano Banana 2 pricing","Google Nano Banana 2","image-to-image API","best image-to-image model"],"description":"Access Google's Nano Banana 2 for image editing on Runflow. Production-ready API with Sentinel scoring. $0.08/images."},"notable_features":null,"content":"## Overview\n\nNano Banana 2 is Google's new state-of-the-art image generation and editing model. Users can expect intelligent editing that respects source composition in production. Automatic provider failover keeps your pipeline running when others go down.","pricing_note":null,"created_at":"2026-04-03T10:03:04.759068Z","updated_at":"2026-04-06T18:40:23.917744Z"},{"id":"019d52cb-a425-7fe3-b2df-49c157f1c3bf","model_creator_id":"019d40e6-d656-7250-8146-1707e98a6c74","slug":"google/nano-banana-pro/edit","name":"Nano Banana Pro — Edit","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/google/nano-banana-pro/edit/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-9572-7d53-b1be-97c00942ca3d","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Nano Banana Pro API — Image Editing Model | Runflow","keywords":["Nano Banana Pro API","Nano Banana Pro pricing","Google Nano Banana Pro","image-to-image API","best image-to-image model"],"description":"Run Nano Banana Pro by Google via Runflow's API. Image editing with Sentinel quality scoring. $0.15/images."},"notable_features":["realism","typography"],"content":"## Overview\n\nNano Banana Pro elevates image editing further — Google's new state-of-the-art image generation and editing model. Expect precision edits that preserve the original's integrity from every generation. Deploy with Runflow and get automatic Sentinel scoring on every output.","pricing_note":null,"created_at":"2026-04-03T10:02:50.790423Z","updated_at":"2026-04-06T18:55:59.230381Z"},{"id":"019d52c2-8761-7682-8e9a-10d2a32ba927","model_creator_id":"019d40e6-d5b1-71b0-9d0c-72636feb2940","slug":"alibaba/qwen-image-edit-2511","name":"Qwen Image Edit 2511","description":"Advanced image editing model from Alibaba. Qwen Image Edit 2511 delivers superior text editing capabilities, multi-image support, and precise visual modifications through natural language instructions. Supports style transfer, object editing, and creative compositions.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/alibaba/qwen-image-edit-2511/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-7552-76f2-b9d1-baa014e9d2dc","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Qwen Image Edit 2511 API — Image Editing Model | Runflow","usage":{"replicate_runs":3588657},"keywords":["Qwen Image Edit 2511 API","Qwen Image Edit 2511 pricing","Alibaba Qwen Image Edit 2511","image-to-image API","best image-to-image model"],"description":"Qwen Image Edit 2511 API — image editing with automatic quality scoring and multi-provider routing on Runflow. $0.03/megapixels."},"notable_features":["stylized","transform"],"content":"## Overview\n\nPurpose-built for image editing, Qwen Image Edit 2511 stands out. Endpoint for Qwen's Image Editing 2511 model. Developed by Alibaba's Tongyi-MAI research lab, it excels at natural-language-guided modifications with context awareness. Deploy with Runflow and get automatic Sentinel scoring on every output.","pricing_note":null,"created_at":"2026-04-03T09:52:53.602318Z","updated_at":"2026-04-08T18:43:51.638532Z"},{"id":"019d52b4-d941-7462-bfaa-a37c05653f21","model_creator_id":"019d4f45-0517-7b20-bae5-c09d16696ee8","slug":"bria/background/remove","name":"Bria Background Remove","description":"Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/bria/background/remove/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-280a-7781-9579-18dd6d8660d8","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Bria RMBG 2.0 API — Image Editing Model | Runflow","keywords":["Bria RMBG 2.0 API","Bria RMBG 2.0 pricing","Bria Bria RMBG 2.0","image-to-image API","best image-to-image model"],"description":"Bria RMBG 2.0 on Runflow — image editing API with quality checks, auto-scaling, and transparent pricing. $0.018/generations."},"notable_features":["background removal","image segmentation","high resolution","utility","rembg"],"content":"## Overview\n\nBria RMBG 2.0 advances image editing further. Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04. Its standout capabilities — trained on licensed data — deliver natural-language-guided modifications with context awareness. Production-ready from day one — metered billing, quality scoring, and failover included.","pricing_note":null,"created_at":"2026-04-03T09:37:57.058218Z","updated_at":"2026-04-08T18:18:23.711626Z"},{"id":"019d52b3-8df6-7ce0-9adb-c7c53c1dd36d","model_creator_id":"019d4f45-157b-7720-9cf0-2911f77da0cd","slug":"topaz/upscale/image","name":"Topaz Upscale — Image","description":"Use the powerful and accurate topaz image enhancer to enhance your images.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/topaz/upscale/image/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-2569-7082-816b-fac248d02e87","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Topaz API — Image Editing Model | Runflow","keywords":["Topaz API","Topaz pricing","Topaz Labs Topaz","image-to-image API","best image-to-image model"],"description":"Run Topaz via Runflow's API. Multi-region failover and Sentinel quality scoring. No GPU management."},"notable_features":["image-to-image"],"content":"## Overview\n\nTopaz Image Upscale is the professional standard for AI-powered image upscaling, recovering detail and sharpness that traditional upscalers and even most AI alternatives cannot match. Trusted by photographers, print houses, and e-commerce platforms, it transforms low-resolution source images into print-ready outputs while preserving natural textures and avoiding the over-sharpened artifacts common in competing tools. Through Runflow, Topaz upscaling integrates directly into generation pipelines — pair it with any image model and let Sentinel validate that upscaled outputs meet your resolution and quality requirements before delivery.","pricing_note":null,"created_at":"2026-04-03T09:36:32.246553Z","updated_at":"2026-04-08T18:18:32.321069Z"},{"id":"019d52ab-2c09-7b82-97bd-27d439b555b7","model_creator_id":"019d40e6-d4bd-75a3-b0fd-28a2e2d6a490","slug":"black-forest-labs/flux-pro/kontext","name":"FLUX Kontext","description":"FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/black-forest-labs/flux-pro/kontext/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-0276-7910-954f-29bef3a8a3d8","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"FLUX Kontext [pro] API, In-Context Image Editing by Black Forest Labs | Runflow","usage":{"replicate_runs":48037122},"keywords":["flux kontext pro api","flux kontext pricing","in context image editing api","ai image editing api","character consistent editing","black forest labs kontext","style transfer api","ai identity preserving editing"],"description":"Run FLUX Kontext [pro] via Runflow's API. 12B-param in-context editor, character consistency, style transfer, $0.04/image. No GPU management, Sentinel quality scoring."},"notable_features":null,"content":"\n## Overview\n\nFLUX Kontext [pro], 12B-param in-context editor. Character consistency, style transfer, local edits. $0.04/image.\n\n## Key capabilities\n\n- **Character consistency without fine-tuning**, Preserves subject identity, style, and brand elements across edits, no LoRA training or per-subject fine-tuning needed.\n- **Up to 8× faster than competitors**, Significantly faster inference than competing in-context editing models while maintaining high-quality results.\n- **Local and global edits in one model**, Handles everything from targeted region edits (change a shirt colour) to full scene transformations (move from studio to beach), no separate models or masks needed.\n- **Multi-turn editing**, Apply successive refinements that maintain visual coherence, each edit builds on the previous one without degrading quality.\n\n## FLUX Kontext model family by Black Forest Labs\n\n| Model | Details |\n|---|---|\n| **FLUX Kontext [max]** | Premium, best prompt adherence and typography, $0.08/image |\n| **FLUX Kontext [pro]** (this model) | Standard, fast in-context editing with character consistency, $0.04/image |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Architecture | Rectified Flow Transformer with reference conditioning |\n| Parameters | 12 billion |\n| Mode | Image-to-image (in-context editing) |\n| Speed | Up to 8× faster than state-of-the-art models |\n| Guidance Scale | 3.5 (default) · 1–20 range |\n| Max Batch Size | 4 images per request |\n| Input Formats | JPG · JPEG · PNG · WebP · GIF · AVIF |\n| Output Formats | JPEG · PNG |\n| License | Commercial |\n    ","pricing_note":null,"created_at":"2026-04-03T09:27:22.890269Z","updated_at":"2026-04-06T18:21:58.186871Z"},{"id":"019d52a7-a9d6-7d32-8947-51a8d53f49a6","model_creator_id":"019d4f45-0bb9-7610-8c54-262e163595cd","slug":"meta/sam-3/image","name":"SAM 3","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/meta/sam-3/image/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da5-fc4b-7fe0-9b70-b9853e47ebee","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Segment Anything Model 3 API — Image Editing Model | Runflow","keywords":["Segment Anything Model 3 API","Segment Anything Model 3 pricing","Meta Segment Anything Model 3","image-to-image API","best image-to-image model"],"description":"Access Meta's Segment Anything Model 3 for image editing on Runflow. Production-ready API with Sentinel scoring. $0.005/units."},"notable_features":["segmentation","mask","real-time"],"content":"## Overview\n\nBuilt by Meta, Segment Anything Model 3 is a image editing model. SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. Users can expect precision edits that preserve the original's integrity in production. Automatic provider failover keeps your pipeline running when others go down.","pricing_note":null,"created_at":"2026-04-03T09:23:32.951576Z","updated_at":"2026-04-05T21:07:39.525590Z"},{"id":"019d52a5-c5f7-7982-9f45-6bb3d6709f37","model_creator_id":"019d52a5-8995-7113-9fb0-35def9b9538e","slug":"elevenlabs/tts/eleven-v3","name":"ElevenLabs TTS v3","description":"Generate text-to-speech audio using Eleven-v3 from ElevenLabs.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/elevenlabs/tts/eleven-v3/card-1.webp","category_code":"text-to-audio","status_code":"active","family_id":"019d5da5-f618-7303-85b5-9cb8f13679ba","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Elevenlabs API — Audio Generation Model | Runflow","usage":{"replicate_runs":26156},"keywords":["Elevenlabs API","Elevenlabs pricing","ElevenLabs Elevenlabs","text-to-audio API","best text-to-audio model"],"description":"Elevenlabs on Runflow — text-to-audio API with quality checks, auto-scaling, and transparent pricing. $0.1/1000 characters."},"notable_features":["audio"],"content":"## Overview\n\nDesigned for audio production, Elevenlabs lets you generate text-to-speech audio using Eleven-v3 from ElevenLabs. Expect high-quality audio synthesis with fine-grained control from every generation. Sentinel quality scoring catches issues before they reach production.","pricing_note":null,"created_at":"2026-04-03T09:21:29.079853Z","updated_at":"2026-04-06T18:21:55.598265Z"},{"id":"019d4f51-87fc-7e33-b792-17c460862873","model_creator_id":"019d40e6-d4bd-75a3-b0fd-28a2e2d6a490","slug":"black-forest-labs/flux-2-klein-4b","name":"FLUX.2 [klein] 4B","description":"Compact 4-billion parameter text-to-image model from Black Forest Labs. Step-distilled to 4 inference steps for sub-second generation. Unifies text-to-image and image editing in a single architecture with Apache 2.0 licensing.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/black-forest-labs/flux-2-klein-4b/card-1.webp","category_code":"text-to-image","status_code":"active","family_id":"019d5da6-060e-7e30-91a0-d7a0b82566a0","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"FLUX.2 Klein 4B API — Sub-Second Image Generation | Runflow","usage":{"replicate_runs":9400000},"keywords":["FLUX Klein API","FLUX.2 Klein 4B","FLUX Klein pricing","fast image generation API","sub-second image generation","Apache 2.0 image model","Black Forest Labs Klein"],"description":"FLUX.2 Klein 4B on Runflow — compact 4B parameter model with sub-second inference, Apache 2.0 license. $0.014/megapixel via single API call."},"notable_features":["Sub-second inference (4 steps)","Apache 2.0 license","Multi-reference editing (up to 4 images)","Transparent background support","Up to 4MP resolution","Text rendering"],"content":"## Overview\n\nFLUX.2 [klein] 4B is a compact, Apache 2.0-licensed image generation model from Black Forest Labs. At 4 billion parameters and just 4 inference steps, it delivers sub-second generation without sacrificing quality. It uses a Mistral 3 VLM text embedder and supports up to 4 megapixel output resolution.\n\n## Key Features\n\n- **Sub-second inference** — distilled to 4 steps for real-time applications\n- **Multi-reference editing** — accepts up to 4 input images for guided generation\n- **Text rendering** — strong text-in-image capabilities inherited from FLUX.2\n- **Transparent backgrounds** — native RGBA PNG output support\n- **Apache 2.0** — fully commercial use permitted\n\n## Architecture\n\nRectified flow transformer with FLUX.2 VAE for pixel-to-latent conversion. The distilled variant uses `guidance_scale=1.0` by default. Requires ~13 GB VRAM (fits on RTX 3090/4070+).\n\n## When to Use\n\nIdeal for high-volume production workloads, real-time applications, consumer-facing products, and edge deployment where speed and commercial licensing matter.","pricing_note":null,"created_at":"2026-04-02T17:50:36.541345Z","updated_at":"2026-04-06T18:21:58.043189Z"},{"id":"019d4f49-4dcc-7b70-977d-9ab9be7dcde7","model_creator_id":"019d4f45-0dda-7773-8854-216f35470402","slug":"openai/gpt-image-1.5","name":"GPT Image 1.5","description":"GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/openai/gpt-image-1.5/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-8460-7673-b345-92045c676346","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"GPT-Image 1.5 API, OpenAI Image Generation Model | Runflow","usage":{"replicate_runs":6765306},"keywords":["gpt image 1.5 api","gpt image 1.5 pricing","openai image generation api","gpt-image api","text to image api","openai text to image","best text to image model","ai image generator api"],"description":"Run GPT-Image 1.5 by OpenAI via Runflow's API. 3 quality tiers × 3 sizes, from $0.009 to $0.200/image. Transparent background support, Sentinel quality scoring."},"notable_features":["openai","gpt-image",""],"content":"\n## Overview\n\nGPT-Image 1.5 by OpenAI, high-fidelity images with strong prompt adherence. Three quality tiers, three sizes, transparent background support. From $0.009/image.\n\n## Key capabilities\n\n- **Quality × size pricing matrix**, Choose low, medium, or high quality at three size options, 9 price points from $0.009 to $0.200 per image, letting you optimise cost for every use case.\n- **Transparent background support**, Native transparent background output, no post-processing removal needed for product photography on white or overlay use cases.\n- **OpenAI's strongest image model**, GPT-Image 1.5 is OpenAI's highest-quality image generation model, built on the same foundation as their multimodal research.\n\n## GPT-Image model family by OpenAI\n\n| Model | Details |\n|---|---|\n| **GPT-Image 1.5 (Generation)** (this model) | Text-to-image with quality × size pricing tiers |\n| **GPT-Image 1.5 (Edit)** | Image editing and inpainting variant |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Architecture | Autoregressive Vision Model |\n| Sizes | 1024×1024 · 1536×1024 · 1024×1536 |\n| Quality Tiers | Low · Medium · High |\n| Background | Auto · Transparent · Opaque |\n| Output Formats | JPEG · PNG · WebP |\n| License | Commercial |\n    ","pricing_note":null,"created_at":"2026-04-02T17:41:37.356807Z","updated_at":"2026-04-13T08:38:04.987185Z"},{"id":"019d40ea-6871-78d2-a89e-dd9fa10725f5","model_creator_id":"019d40e6-d656-7250-8146-1707e98a6c74","slug":"google/nano-banana-pro","name":"Nano Banana Pro","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/google/nano-banana-pro/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-9572-7d53-b1be-97c00942ca3d","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Nano Banana Pro API, Google's Premium Image Generation Model | Runflow","usage":{"replicate_runs":18632071},"keywords":["nano banana pro api","nano banana pro pricing","google nano banana pro","text to image api","best text to image model","google image generation api","ai image generator api"],"description":"Run Nano Banana Pro by Google via Runflow's API. Text-to-image with Sentinel quality scoring. $0.15/image. No GPU management, one API call, production-ready."},"notable_features":["realism","typography"],"content":"\n## Overview\n\nNano Banana Pro by Google, premium image generation with sharp detail and natural lighting. Up to 4K resolution, optional web search. SynthID watermarking on every output.\n\n## Key capabilities\n\n- **Google's premium image generation model**, Nano Banana Pro delivers Google's highest image quality in the Nano Banana family, optimised for sharp detail and natural lighting.\n- **Character consistency up to 5 people**, Maintain consistent character appearance across up to 5 people in a single generation, ideal for storytelling, campaigns, and multi-character scenes.\n- **SynthID watermarking**, Every output carries Google's SynthID digital watermark, invisibly embedded and robust to common edits, enabling attribution and provenance tracking.\n- **Web search grounding**, Optional web search enables generation grounded in current events, recent product releases, and real-time visual references. +$0.015/image.\n- **3 resolution tiers**, 1K, 2K, and 4K resolution options in one model, choose per request based on your quality and cost requirements.\n\n## Nano Banana model family by Google\n\n| Model | Details |\n|---|---|\n| **Nano Banana Pro** (this model) | Premium, highest quality, web search, up to 4K |\n| **Nano Banana 2** | Standard, fast generation from 0.5K to 4K |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Architecture | Gemini 3 Pro Image |\n| Resolutions | 1K · 2K · 4K |\n| Aspect Ratios | 10 standard ratios (21:9 to 9:16) |\n| Add-ons | Web search (+$0.015/image) |\n| Watermarking | SynthID digital watermark |\n| Output Formats | JPEG · PNG · WebP |\n| License | Commercial |\n    ","pricing_note":null,"created_at":"2026-03-30T22:43:17.234284Z","updated_at":"2026-04-13T08:38:04.945771Z"},{"id":"019d40ea-66c5-7f12-9abb-578b7e2497c8","model_creator_id":"019d40e6-d656-7250-8146-1707e98a6c74","slug":"google/nano-banana-2","name":"Nano Banana 2","description":"Nano Banana 2 is Google's new state-of-the-art fast image generation and editing model","version":"1.0.0","icon_url":null,"cover_url":"https://public.runflow.io/images/models/google/nano-banana-2/card-1.webp","category_code":"image-to-image","status_code":"active","family_id":"019d5da6-97d1-77f0-95e4-c8c99fa95013","family_variant_code":null,"param_count":null,"architecture":null,"license_code":"commercial","max_resolution":null,"lora_support":null,"fine_tuning":null,"supports_streaming":null,"paper_url":null,"github_url":null,"is_official":false,"is_open_source":false,"availability_status":null,"seo":{"title":"Nano Banana 2 API, Google Image Generation Model | Runflow","usage":{"replicate_runs":4328652},"keywords":["nano banana 2 api","nano banana 2 pricing","google nano banana 2","nano banana text to image","text to image api","best text to image model","google image generation api","ai image generator api"],"description":"Run Nano Banana 2 by Google via Runflow's API. 4 resolution tiers (0.5K–4K), web search, and thinking modes. From $0.06/image. No GPU management, Sentinel quality scoring."},"notable_features":null,"content":"\n## Overview\n\nNano Banana 2 by Google, fast image generation across 4 resolution tiers (0.5K–4K). Optional web search and thinking modes. SynthID watermarking on every output.\n\n## Key capabilities\n\n- **4 resolution tiers in one model**, From 0.5K (fastest, cheapest) to 4K, choose the right resolution per request without switching models.\n- **14 aspect ratios including extremes**, Native support for 14 ratios from 21:9 to 1:8, including panoramic (8:1) and ultra-tall (1:8) formats with no letterboxing.\n- **Character consistency up to 5 people**, Maintain consistent character appearance across up to 5 people in a single generation, ideal for storytelling, campaigns, and multi-character scenes.\n- **SynthID watermarking**, Every output carries Google's SynthID digital watermark, invisibly embedded and robust to common edits, enabling attribution and provenance tracking.\n- **Web search + thinking modes**, Optional web search grounds generation in current events. Thinking mode adds reasoning for complex prompts, both priced as add-ons.\n\n## Nano Banana model family by Google\n\n| Model | Details |\n|---|---|\n| **Nano Banana 2** (this model) | Standard, fast generation from 0.5K to 4K resolution |\n| **Nano Banana Pro** | Premium, higher quality, web search enabled, up to 4K |\n\n## Technical specifications\n\n| Spec | Details |\n|---|---|\n| Architecture | Gemini 3.1 Flash Image |\n| Resolutions | 0.5K · 1K · 2K · 4K |\n| Aspect Ratios | 14 ratios including extreme (8:1, 1:8, 4:1, 1:4) |\n| Add-ons | Web search · Model thinking |\n| Watermarking | SynthID digital watermark |\n| Output Formats | JPEG · PNG · WebP |\n| License | Commercial |\n    ","pricing_note":null,"created_at":"2026-03-30T22:43:16.808184Z","updated_at":"2026-04-13T08:38:05.010732Z"}],"first":"https://api.runflow.io/v1/public/models","next":null,"previous":null}