Curated ComfyUI workflows ready-to-run now

Create incredible videos from text or images with breakthrough AI running on everyday CPUs.

Create stunningly lifelike image with Flux UltraRealistic LoRA V2

Ultra fast PMRF upscaler! 3.79s on medium machine. 2x scale.

SUPER FAST! 5-second video in 45 seconds!

Reference-driven video generation using Wan2.1 14B

Extract camera movements and human motions from reference videos for professional video generation

Controlled FLUX Dev image generation with Pose, Depth, Canny, and ReColor

Multimodal understanding and generation with open-source AI.

Create, edit and transform videos with the powerful VACE Wan2.1 14B.

Generate studio-quality music 15× faster with breakthrough diffusion technology.

Insert any subject into images with mask or text guidance.

Create dual-subject videos with exceptional identity preservation.

Relight subjects using image-based lighting inputs with LBM.

Transform videos with a reference style image using VACE Wan2.1.

Perform 11 editing operations with natural language in Step1X-Edit.

ICEdit+Nunchaku: A solution for ultra-fast, precise AI image editing.

Create stable and consistent images from subject and object references.

Generate smooth videos from a start and end frame using Wan 2.1 FLF2V.

Empower your AI videos with Wan 2.1 Fun.

High-quality image generation using a 17B parameter model.

Create stable, 60s+ long videos with minimal cloud resources.

Swap faces in images with natural language instructions while preserving style and context.

Sonic delivers advanced audio-driven lip-sync for portraits with high-quality animation.

Create consistent, high-resolution character designs from multiple angles with full control over emotions, lighting, and environments.

Transform your video style by applying the restyled first frame using Wan 2.1 video restyle workflow.

Design motion paths to animate still photos into videos.

Repair distorted faces and upscale images to 4K resolution.

Combine multi elements into dynamic videos with precision.

Dual-mode identity-preserving generation with Face Combine and Zero-Shot workflows using InfiniteYou.

Generate images with precise character control while preserving artistic style.

Advance Wan 2.1 video generation with lightweight depth and tile LoRAs for improved structure and detail.

Generate videos with ControlNet-style visual passes like Depth, Canny, and OpenPose.

Enhance Wan 2.1 video generation with LoRA models for improved style and customization.

Create magnificent movies out of still images through cinematic motion and customizable effects.

Generate consistent images of your character across poses, angles, and styles from a single photo.

Remove video backgrounds with one mask frame for perfect subject isolation.

Use downloaded Hunyuan LoRAs to control style and character consistency in video generation.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Generate cinematic human videos with genuine facial expressions and natural movements from text or images.

Professional face swapping toolkit for ComfyUI that enables natural face replacement and enhancement.

Generate precise textured 3D assets from images with state-of-the-art AI technology.

Turn simple footage into epic film scenes with CogVideoX, ControlNet, and Live Portrait.

Generates videos from text prompts.

Convert an image and a text prompt into a dynamic video.

Create consistent characters and ensure they look uniform using your images.

Generate videos from text prompts or create frame interpolation between two images with Nvidia's Cosmos.

Take your face swapping projects to new heights with Flux PuLID.

Official Flux Tools - Flux Fill for Inpainting and Outpainting

Flux Upscaler – Achieve 4k, 8k, 16k, and Ultimate 32k Resolution!

Generates videos from image+text prompts.

Janus-Pro: Advanced Text-to-Image and Image-to-Text generation.

Transform dance videos with scene editing, face-swapping, and motion preservation.

Create consistent and realistic characters with precise control over facial features, poses, and compositions.

Official Flux Tools - Flux Depth and Canny ControlNet Model

Combine text prompt and source video to generate new video.

Trellis is an advanced Image-to-3D model for high-quality 3D assets generation.

CatVTON for easy and accurate virtual try-on.

Blend FLUX-1 model with FLUX-RealismLoRA for photorealistic AI images

Guide you through the entire process of training FLUX LoRA models using your custom datasets.

Generate high-quality human motion videos with MimicMotion, using a reference image and motion sequence.

Transfer facial expressions and movements from a driving video onto a source video

OmniGen: Modify Images Based on Reference Images and Prompts

Advanced audio-driven lip sync technology.

Effortlessly restyle videos, converting realistic characters into anime while keeping the original backgrounds intact.

Official Flux Tools - Flux Redux for Image Variation and Restyling

A new image generation model developed by Black Forest Labs

Upscale images to 8K with SUPIR and 4x Foolhardy Remacri model.

Create consistent characters and ensure they look uniform by inputting text.

Effortlessly fill, remove, and refine images, seamlessly integrating new content.

MMAudio: Advanced video-to-audio model for high-quality audio generation.

Create stunning 3D content with Stable Fast 3D and ComfyUI 3D Pack.

Transfers the motion and style from a source video onto a target image or object.

Virtual try-on creating realistic results by capturing garment details and style.

CogVideoX Fun: Advanced video-to-video model for high-quality video generation.

Merge visuals and prompts for stunning, enhanced results.

Generate 360-degree views of anything from a single image or description.

Achieve better control with FLUX-ControlNet-Depth & FLUX-ControlNet-Canny for FLUX.1 [dev].

With ComfyUI ReActor, you can easily swap the faces of one or more characters in images or videos.

Create multi-view RGB images first, then transform them into 3D assets.

Elevate your product photography effortlessly, a top alternative to Magnific.AI Relight.

Subject Trajectory Video Demo for CogVideoX

Stable Diffusion 3.5 (SD3.5) for high-quality, diverse image generation.

Relight your videos with light maps and prompts

Edit backgrounds, enhance lighting, and regenerate new scenes easily.

Animate portraits with facial expressions and motion using a single image and reference video.

Use IPAdapter Plus and ControlNet for precise style transfer with a single reference image.

Use customizable parameters to control every feature, from eye blinks to head movements, for natural results.

Fluxtapoz Nodes for RF Inversion and Stylization - Unsampling and Sampling

Generate realistic talking heads and body gestures synced with the provided audio.

Mochi Edit: Modify Videos Using Text-Based Prompts and Unsampling.

Generate 3D content, from multi-view images to detailed meshes.

Explore XLabs FLUX IPAdapter V2 model compared to V1 for your creative goals.

Discover Flux and 10 versatile In-Context LoRA models for image generation.

Including both text-to-video and image-to-video mode.

Audio-driven lip-sync for portrait animation in 4K.

Enhance realism by using ControlNet to guide FLUX.1-dev.

Generate multi-view normal maps and color images for 3D assets.

Use SDXL and FLUX to expand and refine images seamlessly.

Controlling latent noise with Unsampling helps dramatically increase consistency in video style transfer.

Transform your subject with an audioreactive background made of intricate geometries.

Create incredible videos from text or images with breakthrough AI running on everyday CPUs.

SUPER FAST! 5-second video in 45 seconds!

Reference-driven video generation using Wan2.1 14B

Extract camera movements and human motions from reference videos for professional video generation

Create, edit and transform videos with the powerful VACE Wan2.1 14B.

Create dual-subject videos with exceptional identity preservation.

Generate smooth videos from a start and end frame using Wan 2.1 FLF2V.

Empower your AI videos with Wan 2.1 Fun.

Create stable, 60s+ long videos with minimal cloud resources.

Sonic delivers advanced audio-driven lip-sync for portraits with high-quality animation.

Transform your video style by applying the restyled first frame using Wan 2.1 video restyle workflow.

Design motion paths to animate still photos into videos.

Combine multi elements into dynamic videos with precision.

Advance Wan 2.1 video generation with lightweight depth and tile LoRAs for improved structure and detail.

Generate videos with ControlNet-style visual passes like Depth, Canny, and OpenPose.

Enhance Wan 2.1 video generation with LoRA models for improved style and customization.

Create magnificent movies out of still images through cinematic motion and customizable effects.

Remove video backgrounds with one mask frame for perfect subject isolation.

Use downloaded Hunyuan LoRAs to control style and character consistency in video generation.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Generate cinematic human videos with genuine facial expressions and natural movements from text or images.

Erase objects from videos with auto-masking and realistic reconstruction.

Turn simple footage into epic film scenes with CogVideoX, ControlNet, and Live Portrait.

Generates videos from text prompts.

Convert an image and a text prompt into a dynamic video.

Generate videos from text prompts or create frame interpolation between two images with Nvidia's Cosmos.

Generates videos from image+text prompts.

Generate high-quality human motion videos with MimicMotion, using a reference image and motion sequence.

Transfer facial expressions and movements from a driving video onto a source video

Advanced audio-driven lip sync technology.

CogVideoX Fun: Advanced video-to-video model for high-quality video generation.

Subject Trajectory Video Demo for CogVideoX

Animate portraits with facial expressions and motion using a single image and reference video.

Use customizable parameters to control every feature, from eye blinks to head movements, for natural results.

Generate realistic talking heads and body gestures synced with the provided audio.

Mochi Edit: Modify Videos Using Text-Based Prompts and Unsampling.

Including both text-to-video and image-to-video mode.

Audio-driven lip-sync for portrait animation in 4K.

Text to Video Demo Using the Genmo Mochi 1 Model

CogVideoX-5B: Advanced text-to-video model for high-quality video generation.

Object segmentation of videos with unrivaled accuracy.

Input a video and light masks to generate a relighting video

Morphing animation with AnimateDiff LCM, IPAdapter, QRCode ControlNet, and Custom Mask modules.

Use IPAdapter Plus, ControlNet QRCode, and AnimateLCM to create morphing videos quickly.

Create stunning Houdini-like animations with Z-Depth Maps using only 2D image.

ToonCrafter can generate cartoon interpolations between two cartoon images.

Use Blender to set up 3D scenes and generate image sequences, then use ComfyUI for AI rendering.

Render visuals in ComfyUI and sync audio in TouchDesigner for dynamic audio-reactive videos.

Convert images to animations with ComfyUI IPAdapter Plus and ControlNet QRCode.

Leverage the IPAdapter Plus Attention Mask for precise control of the image generation process.

Tested for looping video and frame interpolation. Better than closed-source video gen in certain scenarios

Accelerate your text-to-video animation using the ComfyUI AnimateLCM Workflow.

With IPAdapter, you can efficiently control the generation of animations using reference images.

Batch Prompt schedule with AnimateDiff offers precise control over narrative and visuals in animation creation.

Explore AnimateDiff V3, AnimateDiff SDXL and AnimateDiff V2, and use Upscale for high-resolution results.

Utilize IPAdapters for static image generation and Stable Video Diffusion for dynamic video generation.

Incorporate FreeU with SVD to improve image-to-video conversion quality without additional costs.

Integrate Stable Diffusion and Stable Video Diffusion to convert text directly into video.

Set ControlNet Timestep KeyFrames, such as the first and last frames, to create morphing animations.

Utilize Dynamic Prompts (Wildcards), Animatediff, and IPAdapter to generate dynamic animations or GIFs.

Utilize Prompts Travel with Animatediff for precise control over specific frames within the animation.

Create incredible videos from text or images with breakthrough AI running on everyday CPUs.

Create, edit and transform videos with the powerful VACE Wan2.1 14B.

Design motion paths to animate still photos into videos.

Remove video backgrounds with one mask frame for perfect subject isolation.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Erase objects from videos with auto-masking and realistic reconstruction.

Professional face swapping toolkit for ComfyUI that enables natural face replacement and enhancement.

Turn simple footage into epic film scenes with CogVideoX, ControlNet, and Live Portrait.

Generate videos from text prompts or create frame interpolation between two images with Nvidia's Cosmos.

Transform dance videos with scene editing, face-swapping, and motion preservation.

Combine text prompt and source video to generate new video.

Effortlessly restyle videos, converting realistic characters into anime while keeping the original backgrounds intact.

Transfers the motion and style from a source video onto a target image or object.

With ComfyUI ReActor, you can easily swap the faces of one or more characters in images or videos.

Relight your videos with light maps and prompts

Controlling latent noise with Unsampling helps dramatically increase consistency in video style transfer.

Transform your subject with an audioreactive background made of intricate geometries.

Convert your video into clay style using Unsampling method.

Convert your video into parchment-style animations using Unsampling method.

Transform your subjects and have them travel through different scenes seamlessly.

Transform your subjects and give them pulsating, music-driven auras that dance to the rhythm.

Achieve motion graphics animation effects starting from a pre-existing video input.

Enhance Vid2Vid creativity by focusing on the composition and masking of your original video.

The ComfyUI Vid2Vid offers two distinct workflows to creating high-quality, professional animations: Vid2Vid Part 1, which enhances your creativity by focusing on the composition and masking of your original video, and Vid2Vid Part 2, which utilizes SDXL Style Transfer to transform the style of your video to match your desired aesthetic. This page specifically covers Vid2Vid Part 1

Elevate your videos with a transformation into distinctive ceramic art, infusing them with creativity.

Transform your videos into timeless marble sculptures, capturing the essence of classic art.

Convert the original video into the desired animation by using only a few images to define the preferred style.

Give your videos a playful twist by transforming them into lively cartoons.

Transform your videos into mesmerizing Japanese anime.

Give your videos a unique anime makeover effortlessly, capturing the vibrant flat style

Revolutionize videos into the style of adventure games, bringing the thrill of gaming to life!

Create captivating visual effects with AnimateDiff and ControlNet (featuring QRCode Monster and Lineart).

Enhance VFX with AnimateDiff, AutoMask, and ControlNet for precise, controlled outcomes.

Discover the innovative use of IPAdapter to create stunning motion art.

Create stunningly lifelike image with Flux UltraRealistic LoRA V2

Controlled FLUX Dev image generation with Pose, Depth, Canny, and ReColor

Multimodal understanding and generation with open-source AI.

Relight subjects using image-based lighting inputs with LBM.

Create stable and consistent images from subject and object references.

High-quality image generation using a 17B parameter model.

Swap faces in images with natural language instructions while preserving style and context.

Create consistent, high-resolution character designs from multiple angles with full control over emotions, lighting, and environments.

Repair distorted faces and upscale images to 4K resolution.

Dual-mode identity-preserving generation with Face Combine and Zero-Shot workflows using InfiniteYou.

Generate images with precise character control while preserving artistic style.

Generate consistent images of your character across poses, angles, and styles from a single photo.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Generate precise textured 3D assets from images with state-of-the-art AI technology.

Create consistent characters and ensure they look uniform using your images.

Take your face swapping projects to new heights with Flux PuLID.

Official Flux Tools - Flux Fill for Inpainting and Outpainting

Janus-Pro: Advanced Text-to-Image and Image-to-Text generation.

Create consistent and realistic characters with precise control over facial features, poses, and compositions.

Official Flux Tools - Flux Depth and Canny ControlNet Model

CatVTON for easy and accurate virtual try-on.

Blend FLUX-1 model with FLUX-RealismLoRA for photorealistic AI images

Guide you through the entire process of training FLUX LoRA models using your custom datasets.

OmniGen: Modify Images Based on Reference Images and Prompts

Official Flux Tools - Flux Redux for Image Variation and Restyling

A new image generation model developed by Black Forest Labs

Create consistent characters and ensure they look uniform by inputting text.

Virtual try-on creating realistic results by capturing garment details and style.

Merge visuals and prompts for stunning, enhanced results.

Generate 360-degree views of anything from a single image or description.

Achieve better control with FLUX-ControlNet-Depth & FLUX-ControlNet-Canny for FLUX.1 [dev].

Elevate your product photography effortlessly, a top alternative to Magnific.AI Relight.

Stable Diffusion 3.5 (SD3.5) for high-quality, diverse image generation.

Use IPAdapter Plus and ControlNet for precise style transfer with a single reference image.

Fluxtapoz Nodes for RF Inversion and Stylization - Unsampling and Sampling

Explore XLabs FLUX IPAdapter V2 model compared to V1 for your creative goals.

Discover Flux and 10 versatile In-Context LoRA models for image generation.

Enhance realism by using ControlNet to guide FLUX.1-dev.

Use SDXL and FLUX to expand and refine images seamlessly.

Compare Stable Diffusion 3.5 and FLUX.1 in one ComfyUI workflow.

Adapt pre-trained models to specific image styles for stunning 512x512 and 1024x1024 visuals.

Faster image generation and better resource management.

Create realistic personalized photos from text prompts while preserving identity

utilizes LoRA models, ControlNet, and InstantID for advanced face-to-many transformations

Combine IPAdapter and ControlNet for efficient texture application and enhanced visuals.

Integrate Stable Diffusion 3 medium into your workflow to produce exceptional AI art.

MistoLine adapts to various line art inputs, effortlessly generating high-quality images from sketches.

Omost uses LLM coding to generate precise, high-quality images.

Integrate face identities and control styles seamlessly with PuLID and IPAdapter Plus.

Use IPAdapter Plus for your fashion model creation, easily changing outfits and styles

IPAdapter Plus enables effective style & composition transfer, functioning like a 1-image LoRA.

Use various merging methods with IPAdapter Plus for precise, efficient image blending control.

Use LayerDiffuse to generate transparent images or blend backgrounds and foregrounds with one another.

Utilize Instant ID and IPAdapter to create customizable, amazing face stickers.

InstantID accurately enhances and transforms portraits with style and aesthetic appeal.

Stable Cascade, a text-to-image model excelling in prompt alignment and aesthetics.

Leverage IPAdapter FaceID Plus V2 model to create consistent characters.

Use the Portrait Master for greater control over portrait creations without relying on complex prompts.

Experience fast text-to-image synthesis with SDXL Turbo.

Create, edit and transform videos with the powerful VACE Wan2.1 14B.

Insert any subject into images with mask or text guidance.

Perform 11 editing operations with natural language in Step1X-Edit.

ICEdit+Nunchaku: A solution for ultra-fast, precise AI image editing.

Create stable and consistent images from subject and object references.

Repair distorted faces and upscale images to 4K resolution.

Dual-mode identity-preserving generation with Face Combine and Zero-Shot workflows using InfiniteYou.

Generate images with precise character control while preserving artistic style.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Erase objects from videos with auto-masking and realistic reconstruction.

Professional face swapping toolkit for ComfyUI that enables natural face replacement and enhancement.

Effortlessly fill, remove, and refine images, seamlessly integrating new content.

With ComfyUI ReActor, you can easily swap the faces of one or more characters in images or videos.

Edit backgrounds, enhance lighting, and regenerate new scenes easily.

Efficiently removes backgrounds by comparing BRIA AI's RMBG 1.4 with Segment Anything.

Easily extend images using outpainting node and ControlNet inpainting model.

Ultra fast PMRF upscaler! 3.79s on medium machine. 2x scale.

Repair distorted faces and upscale images to 4K resolution.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Professional face swapping toolkit for ComfyUI that enables natural face replacement and enhancement.

Flux Upscaler – Achieve 4k, 8k, 16k, and Ultimate 32k Resolution!

Upscale images to 8K with SUPIR and 4x Foolhardy Remacri model.

SUPIR enables photo-realistic image restoration, works with SDXL model, and supports text-prompt enhancement.

The CCSR model enhances image and video upscaling by focusing more on content consistency.

The APISR model enhances and restores anime images and videos, making your visuals more vibrant and clearer.

Revive faded photos into vibrant memories, preserving every detail for cherished reminiscence.

Use Face Detailer first for facial restoration, followed by the 4x UltraSharp Model for superior upscaling.

Mesh Graphormer ControlNet corrects malformed hands in images while preserving the rest.

Use ControlNet Tile, 4xUltraSharp, and frame interpolation for a high-resolution outcome.

Generate precise textured 3D assets from images with state-of-the-art AI technology.

Trellis is an advanced Image-to-3D model for high-quality 3D assets generation.

Create stunning 3D content with Stable Fast 3D and ComfyUI 3D Pack.

Create multi-view RGB images first, then transform them into 3D assets.

Generate 3D content, from multi-view images to detailed meshes.

Generate multi-view normal maps and color images for 3D assets.

Use LayerDiffuse for image transparency and TripoSR for quick 3D object creation

Generate studio-quality music 15× faster with breakthrough diffusion technology.

MMAudio: Advanced video-to-audio model for high-quality audio generation.

Create stunningly lifelike image with Flux UltraRealistic LoRA V2

Controlled FLUX Dev image generation with Pose, Depth, Canny, and ReColor

Repair distorted faces and upscale images to 4K resolution.

Generate images with precise character control while preserving artistic style.

Create consistent characters and ensure they look uniform using your images.

Take your face swapping projects to new heights with Flux PuLID.

Official Flux Tools - Flux Fill for Inpainting and Outpainting

Official Flux Tools - Flux Depth and Canny ControlNet Model

Blend FLUX-1 model with FLUX-RealismLoRA for photorealistic AI images

Guide you through the entire process of training FLUX LoRA models using your custom datasets.

Official Flux Tools - Flux Redux for Image Variation and Restyling

A new image generation model developed by Black Forest Labs

Create consistent characters and ensure they look uniform by inputting text.

Effortlessly fill, remove, and refine images, seamlessly integrating new content.

Merge visuals and prompts for stunning, enhanced results.

Achieve better control with FLUX-ControlNet-Depth & FLUX-ControlNet-Canny for FLUX.1 [dev].

Fluxtapoz Nodes for RF Inversion and Stylization - Unsampling and Sampling

Explore XLabs FLUX IPAdapter V2 model compared to V1 for your creative goals.

Discover Flux and 10 versatile In-Context LoRA models for image generation.

Enhance realism by using ControlNet to guide FLUX.1-dev.

Use SDXL and FLUX to expand and refine images seamlessly.

Adapt pre-trained models to specific image styles for stunning 512x512 and 1024x1024 visuals.

Faster image generation and better resource management.

Create dual-subject videos with exceptional identity preservation.

Create magnificent movies out of still images through cinematic motion and customizable effects.

Use downloaded Hunyuan LoRAs to control style and character consistency in video generation.

Generate precise textured 3D assets from images with state-of-the-art AI technology.

Generates videos from text prompts.

Convert an image and a text prompt into a dynamic video.

Combine text prompt and source video to generate new video.

Create multi-view RGB images first, then transform them into 3D assets.

Create incredible videos from text or images with breakthrough AI running on everyday CPUs.

Reference-driven video generation using Wan2.1 14B

Create, edit and transform videos with the powerful VACE Wan2.1 14B.

Transform videos with a reference style image using VACE Wan2.1.

Generate smooth videos from a start and end frame using Wan 2.1 FLF2V.

Empower your AI videos with Wan 2.1 Fun.

Transform your video style by applying the restyled first frame using Wan 2.1 video restyle workflow.

Design motion paths to animate still photos into videos.

Advance Wan 2.1 video generation with lightweight depth and tile LoRAs for improved structure and detail.

Generate videos with ControlNet-style visual passes like Depth, Canny, and OpenPose.

Enhance Wan 2.1 video generation with LoRA models for improved style and customization.

Pre-set all-in-one system for image & video generation, enhancement, and manipulation. Zero setup required.

Transform dance videos with scene editing, face-swapping, and motion preservation.

Elevate your product photography effortlessly, a top alternative to Magnific.AI Relight.

Input a video and light masks to generate a relighting video

Achieve motion graphics animation effects starting from a pre-existing video input.

Create stunning Houdini-like animations with Z-Depth Maps using only 2D image.

Controlling latent noise with Unsampling helps dramatically increase consistency in video style transfer.

Convert your video into clay style using Unsampling method.

Convert your video into parchment-style animations using Unsampling method.

Flux Upscaler – Achieve 4k, 8k, 16k, and Ultimate 32k Resolution!

Relight your videos with light maps and prompts

Transform your subject with an audioreactive background made of intricate geometries.

Transform your subjects and have them travel through different scenes seamlessly.

Transform your subjects and give them pulsating, music-driven auras that dance to the rhythm.

Morphing animation with AnimateDiff LCM, IPAdapter, QRCode ControlNet, and Custom Mask modules.

Transform videos with a reference style image using VACE Wan2.1.

ICEdit+Nunchaku: A solution for ultra-fast, precise AI image editing.

Transform your video style by applying the restyled first frame using Wan 2.1 video restyle workflow.