• Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Tag not found
  • Not enough history (2 snapshots required) to show difference page for this watch.
  • Not enough history (2 snapshots required) to show difference page for this watch.
Not yet seconds ago.
            False
        
Not yet seconds ago
Current error-ing screenshot from most recent request
✨ AI Change Summary

Changed: - anthropic / claude-sonnet-5: runs increased from 85.3K to 85.8K - google / gemini-3.1-flash-tts: runs increased from 148.6K to 148.7K - google / gemini-3.1-flash (multimodal model): runs increased from 32.6K to 32.7K - luma-ray / flare-video: runs increased from 80 to 82 - anthropic / claude-fable-5: runs increased from 177 to 178 - ideogram-ai / ideogram-v4-quality: runs increased from 995 to 1K - runwayml / aleph-2: runs increased from 316 to 319 - xai / grok-imagine-video-1.5: runs increased from 53.6K to 53.9K - recraft-ai / recraft-v4.2: runs increased from 1.7K to 1.8K

          Try HappyHorse 1.0 from Alibaba
              Explore Pricing Enterprise Docs Blog Sign in Try for free
            Menu

      Explore

                Latest
                      black-forest-labs/flux-2-pro

                    FLUX.2 [pro]

                    Black Forest Labs' most advanced image generation model yet.

                    FLUX.2 [pro] delivers realistic high-resolution images with consistent multi-reference editing, precise control, character consistency, and context-aware creativity.

                      Get started
                Blog posts
              View more
                  Popular models

                            fofr / expression-editor

                          Quickly edit the expression of a face

                          1.7M runs

                            vaibhavs10 / incredibly-fast-whisper

                          whisper-large-v3, incredibly fast, powered by Hugging Face Transformers! šŸ¤—

                          36.3M runs

                            prunaai / z-image-turbo

                          Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

                          45.1M runs

                            Official

                            prunaai / p-image-edit

                          A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image

                          32.9M runs

                            Official

                            prunaai / z-image-turbo

                          Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

                          45.1M runs

                            Official
            Not sure where to start? Learn more about Replicate

      Featured models

                    krea / krea-2-medium

                  Foundation image model from Krea, tuned for expressive illustration, anime, and painterly styles. Fast and consistent across artistic directions.

                  2.4K runs

                    Official
                    alibaba / happyhorse-1.0

                  Alibaba's Happy Horse 1.0 generates videos from text prompts or animates a single image into video. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.

                  16.4K runs

                    Official
                    openai / gpt-image-2

                  OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.

                  6.2M runs

                    Official
                    anthropic / claude-opus-4.7

                  Anthropic's most capable model with a step-change improvement in agentic coding, better vision, and stronger multi-step reasoning

                  85.3K runs
                  85.8K runs

                    Official
                    google / gemini-3.1-flash-tts

                  Google's fast, expressive text-to-speech model with 30 voices and 70+ language support

                  148.6K runs
                  148.7K runs

                    Official
                    minimax / music-2.6

                  Generate full-length songs or instrumentals from a text prompt, with optional auto-generated lyrics

                  11.1K runs

                    Official
                    bytedance / seedance-2.0

                  ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control.

                  629.9K runs
                  630.9K runs

                    Official
                    prunaai / p-video-avatar

                  p-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.

                  59.7K runs

                    Official
                    bytedance / seedream-5-lite

                  Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge

                  2.4M runs

                    Official
                    xai / grok-imagine-video

                  Generate videos using xAI's Grok Imagine Video model

                  1.1M runs

                    Official
                    black-forest-labs / flux-2-max

                  The highest fidelity image model from Black Forest Labs

                  2.8M runs

                    Official
                    google / nano-banana-2

                  Google's fast image generation model with conversational editing, multi-image fusion, and character consistency

                  11.2M runs

                    Official

          Official models

          Official models are always on, maintained, and have predictable pricing.

        View all official models

              luma / ray-3.2

              Luma's reasoning video model. Generates cinematic 5s or 10s video from text or images, with native HDR and EXR export for professional production pipelines.

                  80 runs
                  Official
                  82 runs
                  Official

              anthropic / claude-fable-5

              Claude Fable 5 from Anthropic: the next generation of intelligence for the hardest knowledge work and coding problems.

                  177 runs
                  Official
                  178 runs
                  Official

              ideogram-ai / ideogram-v4-quality

              The highest quality Ideogram v4 model. v4 creates images with stunning realism, creative designs, and consistent styles

                  2.8K runs
                  Official

              ideogram-ai / ideogram-v4-balanced

              Balance speed, quality and cost. Ideogram v4 creates images with stunning realism, creative designs, and consistent styles

                  995 runs
                  Official
                  1K runs
                  Official

              runwayml / aleph-2

              Edit one frame to update an entire video. Aleph 2.0 is Runway's in-context video editor: longer clips (up to 30s), multi-shot edits, and image-level precision via keyframe references.

                  316 runs
                  Official
                  319 runs
                  Official

              xai / grok-imagine-video-1.5

              Image-to-video with synchronized audio using xAI's Grok Imagine Video 1.5 preview model

                  53.6K runs
                  Official
                  53.9K runs
                  Official

              krea / krea-2-large

              Krea's flagship foundation image model. Larger and more flexible than Krea 2 Medium, with particular strength in photorealism and expressive artistic styles.

                  616 runs
                  Official

              krea / krea-2-medium

              Foundation image model from Krea, tuned for expressive illustration, anime, and painterly styles. Fast and consistent across artistic directions.

                  2.4K runs
                  Official

              anthropic / claude-sonnet-4.6

              Claude Sonnet 4.6 from Anthropic: a full upgrade to coding, computer use, long-context reasoning, agent planning, knowledge work, and design, with a 1 million token context window in beta.

                  3.4K runs
                  Official

              bytedance / video-upscaler

              Upscale and enhance video up to 4K at 60fps, with scene-aware presets for AI-generated content, short dramas, UGC, and film restoration.

                  2.2K runs
                  Official

              google / gemini-3.5-flash

              Google's fast multimodal model with frontier reasoning across agents, coding, and long-context tasks

                  32.6K runs
                  Official
                  32.7K runs
                  Official

              heygen / avatar-v

              Create realistic talking avatar videos from text with HeyGen's Avatar V engine — the newest, highest-quality avatar engine with cross-reference-driven animation.

                  132 runs
                  Official

              ibm-granite / granite-vision-4.1-4b

              Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint

                  6.6K runs
                  Official

              prunaai / p-video-animate

              p-video-animate animates a reference image with the motion and audio of a source video. Optimized for speed and cost — 5.24s per 1s of video.

                  3.4K runs
                  Official

              recraft-ai / recraft-v4.1-utility-pro

              A faster, lighter Recraft image generation model at ~2048px resolution, optimized for high-volume production. Design taste and prompt accuracy at high resolution with better throughput.

                  420 runs
                  Official

              recraft-ai / recraft-v4.1-utility

              A faster, lighter Recraft image generation model optimized for high-volume and production pipelines. Same design taste as V4.1, built for speed and throughput.

                  443 runs
                  Official

              recraft-ai / recraft-v4.1-pro-svg

              Generate detailed SVG vector graphics from text prompts. Recraft V4.1 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, and scalable to any size.

                  591 runs
                  Official

              recraft-ai / recraft-v4.1-svg

              Generate production-ready SVG vector images from text prompts. Recraft V4.1's design taste applied to vector output — clean geometry, structured layers, and editable paths.

                  1.5K runs
                  Official

              recraft-ai / recraft-v4.1-pro

              Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4.1, with higher resolution for print-ready and large-scale work.

                  1.7K runs
                  Official
                  1.8K runs
                  Official

              recraft-ai / recraft-v4.1

              Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.

                  6.9K runs
                  Official

        I want to…

        View all collections

          Generate images

          Use AI to generate images & photos with an API

            * openai/gpt-image-2
            * bytedance/seedream-4.5
            * black-forest-labs/flux-2-flex
            * and 83 more…

          Caption videos

          Use AI to understand, describe, and caption videos with an API

            * google/gemini-3-flash
            * google/gemini-3.1-pro
            * shreejalmaharjan-27/tiktok-short-captions
            * and 13 more…

          Generate speech

          Use AI for text-to-speech or to clone your voice via API

            * inworld/realtime-tts-2
            * inworld/realtime-tts-1.5-max
            * inworld/realtime-tts-1.5-mini
            * and 36 more…

          Generate images from a face

          Use AI to generate images from a face with an API

            * runwayml/gen4-image
            * black-forest-labs/flux-kontext-pro
            * ideogram-ai/ideogram-character
            * and 28 more…

          Generate videos

          Use AI to generate videos with an API

            * xai/grok-imagine-video-1.5
            * prunaai/p-video
            * kwaivgi/kling-v3-omni-video
            * and 87 more…

          Upscale images with super resolution

          Use AI to upscale and enhance images with an API

            * google/upscaler
            * prunaai/p-image-upscale
            * philz1337x/clarity-pro-upscaler
            * and 32 more…

          Generate music

          Use AI to generate music with an API

            * elevenlabs/music
            * minimax/music-2.5
            * minimax/music-1.5
            * and 14 more…

          Edit any image

          Use AI to edit any image via API

            * bytedance/seedream-4.5
            * openai/gpt-image-1.5
            * bytedance/seedream-4
            * and 36 more…

          Transcribe speech to text

          Use AI to transcribe speech to text with an API

            * victor-upmeet/whisperx
            * openai/gpt-4o-transcribe
            * vaibhavs10/incredibly-fast-whisper
            * and 12 more…

          OCR to extract text from images

          Use AI For Optical Character Recognition (OCR) to extract text from images via API

            * datalab-to/marker
            * lucataco/deepseek-ocr
            * bytedance/dolphin
            * and 15 more…

          Remove backgrounds

          Use AI to remove backgrounds from images and videos with an API

            * lucataco/remove-bg
            * 851-labs/background-remover
            * arielreplicate/robust_video_matting
            * and 11 more…

          FLUX family of models

          FLUX AI models by Black Forest Labs: image generation & editing via API

            * black-forest-labs/flux-2-flex
            * black-forest-labs/flux-2-max
            * black-forest-labs/flux-2-klein-4b
            * and 18 more…

          Restore images

          Use AI to restore images via API

            * megvii-research/nafnet
            * flux-kontext-apps/restore-image
            * piddnad/ddcolor
            * and 24 more…

          Enhance videos

          Use AI to upscale, restore, extend, and enhance videos with an API

            * topazlabs/video-upscale
            * xai/grok-imagine-video-extension
            * philz1337x/crystal-video-upscaler
            * and 8 more…

          Detect NSFW content

          Detect NSFW content in images and text

            * meta/llama-guard-4-12b
            * falcons-ai/nsfw_image_detection
            * m1guelpf/nsfw-filter
            * and 3 more…

          Classify text

          Classify text by sentiment, topic, intent, or safety

            * openai/gpt-5
            * lucataco/gpt-oss-safeguard-20b
            * fofr/prompt-classifier
            * and 2 more…

          Speaker diarization

          Identify speakers from audio and video inputs

            * thomasmol/whisper-diarization
            * victor-upmeet/whisperx
            * rafaelgalle/whisper-diarization-advanced
            * and 6 more…

          Create realistic face swaps

          Replace faces across images with natural-looking results.

            * codeplugtech/face-swap
            * fofr/face-swap-with-ideogram

          Turn sketches into images

          Transform rough sketches into polished visuals

            * bytedance/seedream-4
            * google/nano-banana
            * black-forest-labs/flux-kontext-max
            * and 2 more…

          Generate emojis

          Generate custom emojis from text or images

            * fofr/sdxl-emoji
            * appmeloncreator/platmoji-beta
            * miike-ai/flux-ico
            * and 1 more…

          Generate anime-style images and videos

          Create anime-style characters, scenes, and animations

            * cjwbw/anything-v4.0
            * datacte/proteus-v0.2
            * datacte/proteus-v0.3
            * and 3 more…

          Generate videos from images

          Use AI to generate videos from images with an API

            * bytedance/seedance-2.0
            * alibaba/happyhorse-1.0
            * runwayml/gen-4.5
            * and 51 more…

          Vision models

          Chat with images — visual Q&A, analysis, and reasoning via API

            * google/gemini-3-flash
            * anthropic/claude-4.5-sonnet
            * openai/gpt-4o-mini
            * and 25 more…

          Caption Images

          Use AI to generate captions and descriptions from images with an API

            * google/gemini-3-flash
            * anthropic/claude-4.5-sonnet
            * openai/gpt-5
            * and 28 more…

          Edit your videos

          Use AI to edit, restyle, extend, and remix videos with an API

            * kwaivgi/kling-v3-omni-video
            * luma/reframe-video
            * luma/modify-video
            * and 19 more…

          WAN family of models

          WAN family of models: open-source video, image, and audio generation

            * wan-video/wan-2.2-t2v-fast
            * wan-video/wan-2.5-t2v-fast
            * wan-video/wan-2.5-i2v-fast
            * and 15 more…

          Create 3D content

          Generate 3D objects, meshes, and textures from text or images with an API

            * tencent/hunyuan-3d-3.1
            * hyper3d/rodin
            * fishwowater/trellis2
            * and 13 more…

          Official models

          Official models are always on, predictably priced, and have a stable API.

            * luma/ray-3.2
            * anthropic/claude-fable-5
            * openai/gpt-image-2
            * and 409 more…

          Large Language Models (LLMs)

          Explore Large Language Models (LLMs) for chat, generation & NLP tasks via API

            * google/gemini-3.1-pro
            * anthropic/claude-opus-4.6
            * openai/gpt-5.2
            * and 40 more…

          Try AI models for free

          Try AI Models for free: video generation, image generation, upscaling, and photo restoration

            * luma/reframe-video
            * google/imagen-4
            * black-forest-labs/flux-dev
            * and 10 more…

          Lipsync videos

          Use AI to generate lipsync videos with an API

            * prunaai/p-video-avatar
            * zsxkib/multitalk
            * sync/lipsync-2-pro
            * and 14 more…

          Control image generation

          Use AI to control image generation with an API

            * black-forest-labs/flux-depth-pro
            * black-forest-labs/flux-canny-pro
            * fofr/latent-consistency-model
            * and 20 more…

          Embedding models

          Embedding models for AI search and analysis

            * daanelson/imagebind
            * andreasjansson/clip-features
            * beautyyuyanli/multilingual-e5-large
            * and 13 more…

          Object detection and segmentation

          Use AI object detection and segmentation models to distinguish objects in images & videos

            * schananas/grounded_sam
            * meta/sam-2-video
            * cjwbw/semantic-segment-anything
            * and 16 more…

          Flux fine-tunes

          Flux fine-tunes: build and run custom AI image models via API

            * bytedance/hyper-flux-8step
            * adirik/flux-cinestill
            * fofr/flux-mona-lisa
            * and 247 more…

          Kontext fine-tunes

          Kontext fine-tunes: Build custom AI image models with an API

            * maikocode/ascii-style
            * lucataco/kontext-realearth
            * valllllex/cartoonia_3d
            * and 9 more…

          Create songs with voice cloning

          Create songs with voice cloning models via API

            * zsxkib/realistic-voice-cloning
            * zsxkib/create-rvc-dataset
            * replicate/train-rvc-model
            * and 3 more…

          Media utilities

          AI media utilities: auto-caption, watermark, frame extraction & more via API

            * fictions-ai/autocaption
            * falcons-ai/nsfw_image_detection
            * charlesmccarthy/addwatermark
            * and 18 more…

          Qwen-Image fine-tunes

          Browse the diverse range of qwen-image fine-tunes the community has custom-trained on Replicate.

            * ccchot-osk103/pai_qwen_21102568
            * ccchot-osk103/moneycat
            * ccchot-osk103/buacat
            * and 18 more…

      Latest models

          * Home
          * About
          * Changelog
          * Join us
          * Terms
          * Privacy
          * Status
          * Support

                luma / ray-3.2

              Luma's reasoning video model. Generates cinematic 5s or 10s video from text or images, with native HDR and EXR export for professional production pipelines.

              80 runs
              82 runs

                Official

                anthropic / claude-fable-5

              Claude Fable 5 from Anthropic: the next generation of intelligence for the hardest knowledge work and coding problems.

              177 runs
              178 runs

                Official

                dannyboy2323 / character-hater

              7 runs

                dannyboy2323 / character-daddanny23

              23 runs

                dannyboy2323 / character-danielbull23

              29 runs

                bencevans / megadetector-v1000-redwood

              Detect Animals, Humans and Vehicles in Camera Trap Imagery with MegaDetector v1000 Redwood

              6 runs

                ideogram-ai / ideogram-v4-quality

              The highest quality Ideogram v4 model. v4 creates images with stunning realism, creative designs, and consistent styles

              2.8K runs

                Official

                ideogram-ai / ideogram-v4-balanced

              Balance speed, quality and cost. Ideogram v4 creates images with stunning realism, creative designs, and consistent styles

              995 runs
              1K runs

                Official

                runwayml / aleph-2

              Edit one frame to update an entire video. Aleph 2.0 is Runway's in-context video editor: longer clips (up to 30s), multi-shot edits, and image-level precision via keyframe references.

              316 runs
              319 runs

                Official

                birgit-ploeger / birgit-portrait

              85 runs

                xai / grok-imagine-video-1.5

              Image-to-video with synchronized audio using xAI's Grok Imagine Video 1.5 preview model

              53.6K runs
              53.9K runs

                Official

                oitoito / mask2former

              Facebook Mask2Former trained on ADE 20k Dataset

              56 runs

      Load more

          How to prompt Grok Imagine Video 1.5

          Grok Imagine Video 1.5 is the most exciting video model release from xAI. You can generate realistic video with synchronized audio in a single pass, capable of juggling complex motion with precise prompt adherence. We pushed it hard across a range of scenes, and came up with the ultimate prompting guide to get the most out of this model.

            May 21, 2026

          How to make remarkable videos with Seedance 2.0

          If you have never tried a video model before, now is the time.

            April 15, 2026

          How to prompt Seedream 5.0

          Seedream 5.0 brings multi-step reasoning, example-based editing, and deep domain knowledge to image generation. Here's what you should know.

            February 24, 2026
Tip: Highlight text to share or add to ignore lists.  — Download difference patch
For now, Differences are performed on text, not graphically, only the latest screenshot is available.
Screenshot requires Playwright/WebDriver enabled