Run this workflow on InstaSD
Get started in minutes! Run this ComfyUI workflow online - no setup required.
Description
Unleash the full potential of Wan Image-to-Video (I2V) with this ultimate all-in-one animation workflow that merges several beloved effectsβCrush, Rotate 360, Cakeify, Muscle, Inflate, and Squishβinto one seamless system. Ideal for creators aiming to generate high-quality character transformation or stylized animation from a single image with minimal setup.
π― Features
- All-in-One Workflow β Combines multiple popular Wan I2V effects (Crush, Rotate, Cakeify, Muscle, Inflate, Squish) in one setup.
- Real-Time Video Generation β Converts a single input image into a dynamic animation using ComfyUI + VHS.
- High Customization β Uses flexible positive prompts to easily guide specific transformation styles.
- CLIP Vision Integration β Ensures visual consistency by using image embedding alongside text prompts.
- Multi-Effect Control β Swap between effects by switching workflow conditionings or prompt structures.
- High Quality Output β Powered by
wan2.1_i2v_480p_14B_fp8_scaled
for optimized animation fidelity.
π‘ Use Cases
- Character Animation β Transform a static character into a dynamic animated effect with one click.
- Stylized FX Shorts β Quickly prototype or produce quirky and fun animated sequences for social media or motion design.
- VTuber/Influencer Content β Create quick transformations or visual gags for livestream or short-form content.
- Experimental AI Art β Combine squash-and-stretch, muscle morphs, or surreal inflation for artistic expression.
- Looped Effects for Video Edits β Use output as overlays or inserts in video montages.
βοΈ How It Works
- Load the Workflow β Import the
.json
ComfyUI file corresponding to the combined effect version. - Choose an Input Image β Use the
LoadImage
node to select your character base. - Set Prompts β Adjust the positive/negative prompt nodes for desired effect (e.g., "inflated body", "crushed pose", "cake texture").
- Modify Settings (Optional) β Customize sampler steps, frames, model strength, or add LoRA effects.
- Generate Video β Run the flow to generate frames and compile them via the
VHS_VideoCombine
node. - Preview & Export β Output will be saved as an MP4 in your ComfyUI output folder with loop options.
Credits: Pixaroma
Models
File | Destination | Source |
---|---|---|
wan2.1_i2v_480p_14B_fp8_scaled.safetensors | /ComfyUI/models/unet | Download |
squish_18.safetensors | /ComfyUI/models/loras | Download |
umt5_xxl_fp8_e4m3fn_scaled.safetensors | /ComfyUI/models/clip_vision | Download |
wan_2.1_vae.safetensors | /ComfyUI/models/vae | Download |
clip_vision_h.safetensors | /ComfyUI/models/clip_vision | Download |
umt5_xxl_fp8_e4m3fn_scaled.safetensors | /ComfyUI/models/text_encoders | Download |
inflate_20_epochs.safetensors | /ComfyUI/models/loras | Download |
rotate_20_epochs.safetensors | /ComfyUI/models/loras | Download |
cakeify_16_epochs.safetensors | /ComfyUI/models/loras | Download |
crush_20_epochs.safetensors | /ComfyUI/models/loras | Download |
muscle_18_epochs.safetensors | /ComfyUI/models/loras | Download |
Nodes
VAEDecodeCLIPVisionEncodeCLIPTextEncodeVHS_VideoCombineUNETLoaderMarkdownNoteWanImageToVideoVAELoaderNoteCLIPVisionLoaderLoadImageCLIPLoaderKSamplerLoraLoaderModelOnly