VAE
Wan2_1_ VAE_ bf16. safetensors
Wan2 1 VAE BF16 · VAE for ComfyUI
- File
Wan2_1_VAE_bf16.safetensors- Type
- VAE
- Size
- 254 MB
- Folder
ComfyUI/models/vae/- Source
- Comfy-Org/Wan-Animate-2
- SHA-256
1ab9a32cc2c7…
11 workflows use this file
What is Wan2 1 VAE BF16?
Wan2 1 VAE BF16 is a VAE (Variational Autoencoder) that encodes and decodes latent representations. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Wan2 1 VAE BF16 with other models and custom nodes to build any pipeline you need. There are 11 official ComfyUI workflow templates that use Wan2 1 VAE BF16, ready to load and customize.
Workflows for this file
- SAM3, Wan2.1 VACE
Change Any Objects
Uses this file - Wan2.1 InfiniteTalk
InfiniteTalk: Audio-Driven Full-Body Video Dubbing
Uses this file - Wan2.1 VACE
Video Restyle
Uses this file - Wan2.1
Animation Trajectory Control
Uses this file - Wan2.1, Wan
Wan2.1 VACE Inpainting
- Wan2.1, Wan
Wan2.1 VACE Control Video
- Wan2.1, Wan
Wan 2.1 Text to Video
- Wan2.1, Wan
Wan 2.1 Image to Video
Frequently Asked Questions
Wan2 1 VAE BF16 is a VAE (Variational Autoencoder) that encodes and decodes latent representations. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Wan2 1 VAE BF16 with other models and custom nodes to build any pipeline you need. There are 11 official ComfyUI workflow templates that use Wan2 1 VAE BF16, ready to load and customize.
Open ComfyUI and browse any of the 11 official ComfyUI workflow templates that use Wan2 1 VAE BF16. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 11 official ComfyUI workflow templates that use Wan2 1 VAE BF16. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Wan2 1 VAE BF16 weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.