VAE
ace_1. 5_ vae. safetensors
Ace 1.5 Vae · VAE for ComfyUI
- File
ace_1.5_vae.safetensors- Type
- VAE
- Size
- 337 MB
- Folder
ComfyUI/models/vae/- Source
- Comfy-Org/ACE-Step-1.5
- SHA-256
6de92e3a862a…
6 workflows use this file
What is Ace 1.5 Vae?
Ace 1.5 Vae 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 Ace 1.5 Vae with other models and custom nodes to build any pipeline you need. There are 6 official ComfyUI workflow templates that use Ace 1.5 Vae, ready to load and customize.
Workflows for this file
- ACE-Step
ACE-Step 1.5XL Turbo: Text to Music
Uses this file - ACE-Step
ACE-Step 1.5 Music Generation Workflow
Uses this file - ACE-Step
ACE-Step 1.5XL SFT: Text to Music
Uses this file - ACE-Step
ACE-Step 1.5XL Base: Text to Music
Uses this file - ACE-Step
ACE-Step 1.5 Music Generation (4B LLM )
Uses this file - ACE-Step
ACE-Step 1.5 Music Generation AIO
- ACE-Step
ACE Step v1 M2M Editing
- ACE-Step
ACE-Step v1 Text to Instrumentals Music
Frequently Asked Questions
Ace 1.5 Vae 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 Ace 1.5 Vae with other models and custom nodes to build any pipeline you need. There are 6 official ComfyUI workflow templates that use Ace 1.5 Vae, ready to load and customize.
Open ComfyUI and browse any of the 6 official ComfyUI workflow templates that use Ace 1.5 Vae. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 6 official ComfyUI workflow templates that use Ace 1.5 Vae. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Ace 1.5 Vae 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.