demobook

ComfyUI: Image-to-video generation with Wan 2.2

ComfyUITry it →Watch full video →pixaroma ·

Demo summary

The user demonstrates how to use the Wan 2.2 GGUF model in ComfyUI to animate a static image of a woman based on a detailed text prompt.

Step-by-step

  1. Download both high-noise and low-noise GGUF model files for Wan 2.2
  2. Place the diffusion models in a dedicated 'wan 2.2' folder inside the 'diffusion_models' directory
  3. Download and place the text encoder and VAE models into their respective ComfyUI folders
  4. Open ComfyUI and press 'R' to refresh node definitions to see the new models
  5. Select the matching Q-version for both the high-noise and low-noise UNET loader nodes
  6. Load a source image into the workflow
  7. Enter a detailed text prompt describing subject movement, camera motion, and lighting
  8. Adjust the resolution and duration settings before clicking to generate

Options

  • Choose different GGUF sizes (Q-versions) to fit your GPU VRAM
  • Install missing custom nodes via the ComfyUI Manager if they don't appear automatically
  • Use 'Video Combine' node instead of the standard 'Save Image' node for output

Watch out for

  • Wan 2.2 requires two separate diffusion files (high-noise and low-noise) to function
  • The model currently only supports a maximum resolution of HD (not Full HD)
  • Video duration is limited to a maximum of 5 seconds
  • Wan 2.2 models require 16 frames per second rather than 24 to work correctly

Tips

  • Download the same Q-version for both the high and low noise models to maintain consistency
  • Use Q4 models if you only have an 8 GB VRAM card
  • Ensure you have more than 32 GB of system RAM for better model loading performance
  • Describe the movement and camera angles in high detail in the prompt for better results

Highlights

“Like Comfy UI wasn't already complex enough, you always need a high noise and a low-noise model to work.”

All demos from “ComfyUI Video Models: InfiniteTalk + Wan 2.2 + SCAIL + LTX-2 (Ep06)”

  1. 5:244:57Image-to-video generation with Wan 2.2CurrentThe user demonstrates how to use the Wan 2.2 GGUF model in ComfyUI to animate a static image of a woman based on a detailed text prompt.ComfyUIImage to Video
  2. 13:071:21Applying LoRA to Wan 2.2 video generationThe video shows how to integrate a LoRA (Low-Rank Adaptation) into a Wan 2.2 workflow to achieve specific cinematic movements like a face zoom.ComfyUIAI Animation Generator
  3. 15:344:59Character replacement with Wan AnimateThe creator demonstrates using Wan Animate and SAM 3 to mask a character in a reference video and replace them with a new character from a static image while maintaining the original motion.ComfyUIVideo to Video
  4. 21:072:43Cartoon animation with Wan SCAILThe user shows how to animate a cartoon ballerina using a real-person video as a motion reference via the Wan SCAIL workflow in ComfyUI.ComfyUIVideo to Video
  5. 25:063:04Create talking avatars with InfiniteTalkThe demonstration shows how to sync a static character image with an audio file to create a talking avatar using the InfiniteTalk model and Wan 2.1.ComfyUIAI Avatar Video Generator
  6. 31:133:44Text-to-video with LTX-2The video walks through setting up the LTX-2 model in ComfyUI to generate high-resolution video clips from text prompts and images.ComfyUIAI Animation Generator
  7. 36:000:39Singing characters with LTX-2 and custom audioThe creator demonstrates how to use LTX-2 to make a character sing by providing a custom audio file and a specific singing prompt.ComfyUIAI Lip Sync Generator
  8. 37:281:08Upscale video with Seed-V2The user demonstrates upscaling a low-resolution AI-generated video to Full HD using the Seed-V2 workflow in ComfyUI for improved sharpness.ComfyUIAI Video Upscaler
  9. 39:075:27Cloud-based ComfyUI on RunPod/RunHubThe video shows how to run complex video workflows in the cloud using RunHub AI, demonstrating the interface and execution of InfiniteTalk and Wan 2.2 without local hardware.ComfyUIAI Animation Generator
  10. 44:340:52Frame interpolation for smoother motionThe user demonstrates a workflow to double the frame rate of a 16fps video to 32fps to create smoother motion in AI-generated clips.ComfyUIAI Video Interpolation
  11. Watch “ComfyUI Video Models: InfiniteTalk + Wan 2.2 + SCAIL + LTX-2 (Ep06)” →

Image to Video

  1. 7:500:28Image-to-Video action testThe creator demonstrates image-to-video capabilities by uploading a static image and prompting for an intense fight scene in both Hunyuan and Wan models.AI Search
  2. 24:303:12Image-to-Video workflow in ComfyUIA demonstration of the image-to-video workflow in ComfyUI, including uploading a source image, setting crop dimensions, and generating an animated anime scene.AI Search
  3. 10:194:27Image-to-Video with LTX 2.3The creator demonstrates bringing a static image of a vampire warlord to life by using an image input node and a descriptive prompt to guide the animation and environmental effects.AIKnowledge2Go
  4. 6:160:38Image-to-video generation with LTX-2.3The creator demonstrates the image-to-video workflow in ComfyUI, showing how starting from an input image improves text legibility and subject consistency in the final video.MDMZ
  5. 5:244:57Image-to-video generation with Wan 2.2CurrentThe user demonstrates how to use the Wan 2.2 GGUF model in ComfyUI to animate a static image of a woman based on a detailed text prompt.pixaroma
  6. 6:300:17Advanced multi-node AI workflowsThe video shows a complex Roboneo setup where an image is generated, passed through an image editing node, and finally converted into a video.Malva AI
  7. 3:070:38Image to Video with LTX DirectorThe creator demonstrates dragging an image into the LTX Director timeline and entering a text prompt to generate a video of a woman waving her hand.What Dreams Cost
  8. 6:130:36Animate posters using Luma and Kling nodesThe demonstration shows how to chain a video generation node (Luma and Kling/Seance) to the end of an image workflow to animate the final poster design.Sebastian Kamph
  9. 23:511:57Animate 3D renders with Wan 2.1The creator walks through a Wan 2.1 video generation workflow in ComfyUI, using the Painterly I2V node to control motion speed and animate a static 3D render.Matt Hallett Visual
  10. 0:171:00LTX-2 Image-to-Video distilled workflow setupThe demonstrator walks through loading the LTX-2 distilled checkpoint, upscaling models, and Gemma CLIP text encoder, while configuring resolution and frame rates for video generation.LTX
  11. 5:064:11Animate an image using Wan 2.1 in ComfyUIThe creator demonstrates loading a 'native image to video' workflow in ComfyUI, uploading a source image, and using the Wan 2.1 14B model to generate a high-quality video of a woman walking.Danish Sofi
  12. 10:201:00Generate AI video of a horse with Wan 2.1A second demonstration showing the image-to-video process where a static image of a horse is animated into a walking sequence using the Wan 2.1 model in ComfyUI.Danish Sofi
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingMusic & AudioSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co