Create Anime Series Using Anisora WAN Model in ComfyUI - One Click Installer

Bring your images to life and create an anime series using the Anisora 3.2 WAN model.

The Anisora WAN model is an advanced, open-source AI video generation system designed specifically for anime-style animation. Developed with spatiotemporal masking techniques and a unified data pipeline, it seamlessly transforms static images or prompts into fluid, consistent anime video clips. The AniSora installer bundles optimized models and a streamlined ComfyUI interface to simplify setup—making professional-grade animation accessible, even with low VRAM hardware.

The installer is portable and pre-configured, requiring no manual ComfyUI setup. All essential custom nodes and model files are automatically downloaded. The workflow is modular and fast: toggling options and the Fast Groups Bypasser let you adapt tasks for creativity or speed. Input detailed scene prompts; for best results, leverage an LLM to enhance prompt structure.
​
Preloaded Models within the Installer (Low VRAM)
umt5-xxl-encoder-Q5_K_M.gguf (ComfyUI\models\clip)
Hugging Face Link
wan_2.1_vae.safetensors (ComfyUI\models\vae)
Hugging Face Link
Index-Anisora-V3.2-Low-Q3_K_M.gguf (ComfyUI\models\unet)
Hugging Face Link
Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors (ComfyUI\models\loras)
Hugging Face Link
2xLexicaRRDBNet_Sharp.pth Upscale model (ComfyUI\models\upscale_models)
Hugging Face Link
 
Note: The standard high-fidelity Wan2.2-Index-Anisora diffusion models (FP16 and FP8) are not included in the installer for size reasons. For best results, download them separately from Kijai’s Hugging Face repository!
WAN 2.2 Animate Diffusion Model Downloads
Find the full FP16/FP8 diffusion backbone here for enhanced output:
Kijai Wan2.2 Anisora Diffusion Models.
 
Speed
 
Generate crisp AI-animated 2–3 second 480p videos in roughly 4 minutes on an RTX 4050 6GB VRAM GPU. The workflow dynamically adapts to your system, so faster render times and higher resolutions (720p/24fps) are achievable with higher-end GPUs (like RTX 4090).
 
Custom Node w/ command needed for Portable ComfyUI Windows package
ComfyUI Manager - https://github.com/ltdrdata/ComfyUI-Manager
Command to install requirements:
.\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-Manager\requirements.txt
 
System Requirements
Nvidia RTX 30XX, 40XX, or 50XX series GPU (FP16 support required; GTX 10XX/20XX not tested)
CUDA-compatible GPU (minimum 6GB VRAM; more recommended)
Windows OS
At least 40GB free storage.
 
What’s Included
Portable, pre-configured ComfyUI and Wan2.2 Anisora install—no manual ComfyUI setup.
Automated download of all custom nodes and required models.
Workflow designed for simplicity and speed, including easy toggling and modular Fast Groups Bypasser for custom tasks.
 
Usage Notes:
You can utilize either the WAN 2.2 Anisora GGUF models or the standard WAN 2.2 Anisora diffusion models in the workflow.
Enable or disable workflow sections using the levers in the Fast Groups Bypasser node on the left side of the workflow.
Enter your detailed descriptive text prompt for the scene you want to generate.
For best results, enhance your prompt with an LLM.