| File | wan_2.1_vae.safetensors |
| What it is | Wan 2.1 VAE (VAE) |
| Size | 0.3 GB |
| Folder | ComfyUI/models/vae/ |
| Loader node | Load VAE (VAELoader) |
| Source | Comfy-Org/Wan_2.1_ComfyUI_repackaged on Hugging Face |
Download wan_2.1_vae.safetensors (0.3 GB)
Where to put it
Put the file in ComfyUI/models/vae/ (in the portable version: ComfyUI_windows_portable/ComfyUI/models/vae/). Then press R in ComfyUI, or restart it, so the file shows up in Load VAE (VAELoader).
If a workflow says “Value not in list” for this node, the file name in the workflow is different from yours, or the file is in another folder. Click the node and pick the file from the list.
What it does
The VAE turns the finished latent into pixels (and pixels into latents, for image-to-image and editing). It is small, but each model family needs its own: a VAE from another family gives grey, noisy or coloured-noise images.
Models that use wan_2.1_vae.safetensors
| Model | Type | Fits from | Runs well from |
|---|---|---|---|
| Wan 2.1 I2V 14B 480P | video | 13 GB | 21 GB |
| Wan 2.1 I2V 14B 720P | video | 16 GB | 24 GB |
| Wan 2.1 T2V 1.3B | video | 4 GB | 5 GB |
| Wan 2.1 T2V 14B | video | 12 GB | 19 GB |
| Wan 2.1 VACE 14B | video | 13 GB | 24 GB |
| Wan 2.2 Animate 14B | video | 12 GB | 23 GB |
| Wan 2.2 I2V A14B | video | 10 GB | 19 GB |
| Wan 2.2 S2V 14B | video | 15 GB | 22 GB |
| Wan 2.2 T2V A14B | video | 10 GB | 19 GB |
VRAM of the graphics card, for the model with the file this site picks for that card. Open a model to see every file and every GPU.
Other versions of this VAE
| File | Precision | Size | Used by |
|---|---|---|---|
| Wan2_1_VAE_bf16.safetensors | BF16 | 0.3 GB | 2 models |
| wan_2.1_vae.safetensors | — | 0.3 GB | 9 models |
Same encoder, different precision. Any of them works in the same loader node; pick one and select it in the node.
Tested with this file
I use this exact file in 2 of my free workflows, measured on an RTX 5060 Ti 16 GB:
- Wan 2.2 T2V 14B — FP8 — 19 min for an 81-frame 832×480 clip
- Wan 2.2 T2V 14B — GGUF Q5_K_M — 26 min for an 81-frame 832×480 clip
Not sure your card can run these models? Check your GPU. All shared files: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).