Audio-to-Audio
Diffusers
ACE-Step
English
audio
music
vae
autoencoder
ace-step
decoder
oobleck
music-generation
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("megagrump/Ace-Step-1.5-ScragVAE-ComfyUI", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]ScragVAE — Improved VAE Decoder for ACE-Step 1.5
A fine-tuned AutoencoderOobleck decoder with an intent to improve audio fidelity for the ACE-Step 1.5 music generation pipeline. Drop-in compatible with all existing ACE-Step DiT checkpoints.
This is a conversion of the original ScragVAE that makes it usable with ComfyUI.
- Downloads last month
- 821