VAE
ltx-2. 5- audio- vae- bf16. safetensors
Ltx 2.5 Audio Vae BF16 · VAE for ComfyUI
- File
ltx-2.5-audio-vae-bf16.safetensors- Type
- VAE
- Size
- 365 MB
- Folder
ComfyUI/models/vae/- Source
- Lightricks/LTX-2.5
4 workflows use this file
What is Ltx 2.5 Audio Vae BF16?
Ltx 2.5 Audio 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 Ltx 2.5 Audio Vae BF16 with other models and custom nodes to build any pipeline you need. There are 4 official ComfyUI workflow templates that use Ltx 2.5 Audio Vae BF16, ready to load and customize.
Workflows for this file
- LTX-2.3, Lightricks
LTX-2.3: Image to Video
- Wan, Wan2.2
Wan 2.2 14B Image to Video
- LTX-2.3
LTX-2.3: Image Audio to Video
- LTX-2.3, Lightricks
LTX-2.3: Text to Video
- Wan2.2, Wan
Wan 2.2 5B Video Generation
- Wan2.2, Wan
Wan 2.2 14B Text to Video
- Wan2.2, Wan
Wan 2.2 14B First-Last Frame to Video
- Wan2.1, Wan
Wan2.1 VACE Inpainting
Frequently Asked Questions
Ltx 2.5 Audio 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 Ltx 2.5 Audio Vae BF16 with other models and custom nodes to build any pipeline you need. There are 4 official ComfyUI workflow templates that use Ltx 2.5 Audio Vae BF16, ready to load and customize.
Open ComfyUI and browse any of the 4 official ComfyUI workflow templates that use Ltx 2.5 Audio Vae BF16. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 4 official ComfyUI workflow templates that use Ltx 2.5 Audio Vae BF16. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Ltx 2.5 Audio 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.