Model reference · open weights
Wan_2.2_ComfyUI_Repackaged is an open-weight video model from Comfy-Org. Wan_2.2_ComfyUI_Repackaged (BF16) weighs 729 GB; it needs more than the reference configurations below.
Summary of the Comfy-Org/Wan_2.2_ComfyUI_Repackaged model card, 2026-10-01
What it is
| Released by | Comfy-Org |
|---|---|
| Released | 2025-07-27 |
| VRAM | 729 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … B200 180 GB | does not fit |
From the model card
Repackaged model files for ComfyUI.
Original model repository:
Place the files in the following folders:
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 audio_encoders/
│ │ └── wav2vec2_large_english_fp16.safetensors
│ ├── 📂 diffusion_models/
│ │ ├── chrono_edit_14B_fp16.safetensors
│ │ ├── wan2.2_animate_14B_bf16.safetensors
│ │ ├── wan2.2_animate_14B_int8_convrot.safetensors
│ │ ├── wan2.2_fun_camera_high_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_camera_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_camera_low_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_camera_low_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_control_5B_bf16.safetensors
│ │ ├── wan2.2_fun_control_high_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_control_low_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_control_low_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_inpaint_5B_bf16.safetensors
│ │ ├── wan2.2_fun_inpaint_high_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_inpaint_low_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_vace_high_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_vace_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_fun_vace_low_noise_14B_bf16.safetensors
│ │ ├── wan2.2_fun_vace_low_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_i2v_high_noise_14B_fp16.safetensors
│ │ ├── wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_i2v_low_noise_14B_fp16.safetensors
│ │ ├── wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_s2v_14B_bf16.safetensors
│ │ ├── wan2.2_s2v_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_t2v_high_noise_14B_fp16.safetensors
│ │ ├── wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
│ │ ├── wan2.2_t2v_low_noise_14B_fp16.safetensors
│ │ ├── wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
│ │ └── wan2.2_ti2v_5B_fp16.safetensors
│ ├── 📂 loras/
│ │ ├── chronoedit_distill_lora.safetensors
│ │ ├── wan2.2_animate_14B_relight_lora_bf16.safetensors
│ │ ├── wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors
│ │ ├── wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors
│ │ ├── wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors
│ │ └── wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors
│ ├── 📂 text_encoders/
│ │ ├── umt5_xxl_fp16.safetensors
│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
│ ├── 📂 vae/
│ │ ├── wan2.2_vae.safetensors
│ │ └── wan_2.1_vae.safetensors
Examples: https://comfyanonymous.github.io/ComfyUI_examples/wan22/
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Wan 2.2 14B Image to Video: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “Wan 2.2 14B Image to Video” (35.4 GB)
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/vae/wan_2.1_vae.safetensors vae
get Comfy-Org/Wan_2.1_ComfyUI_repackaged split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors text_encoders
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors diffusion_models
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors diffusion_models
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors loras
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors loras
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT