import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("DanielMarius/dms-ace-step-v1-5-vae", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]ACE-Step 1.5 VAE
The ACE-Step 1.5 VAE safetensors checkpoint and its configuration.
Files and local identity
config.json— 425 bytes; SHA-25614e019904df567f26df750317a70e2bd08f9f8f3c40ff4a24c97d1cd3f20ccd2diffusion_pytorch_model.safetensors— 337431388 bytes; SHA-256da17edb604c40deaf09e9b24974e590d1ca83a374070e5d0884cfa4bed9a99b0
Upstream copies and provenance
- Related upstream: ACE-Step/Ace-Step1.5.
- Exact byte match for
config.json: ACE-Step/Ace-Step1.5/vae/config.json; SHA-25614e019904df567f26df750317a70e2bd08f9f8f3c40ff4a24c97d1cd3f20ccd2. - Exact byte match for
diffusion_pytorch_model.safetensors: ACE-Step/Ace-Step1.5/vae/diffusion_pytorch_model.safetensors; SHA-256da17edb604c40deaf09e9b24974e590d1ca83a374070e5d0884cfa4bed9a99b0.
License and use
License metadata follows the identified upstream license mit. Upstream terms and attribution requirements apply; this repository does not claim ownership of upstream model weights.
Provenance audit
Generated from local DMS model assets. Audit run: dms-model-assets-publish-20261022T0750Z-v7. SHA-256 values identify the local source bytes.
- Downloads last month
- 15
Model tree for DanielMarius/dms-ace-step-v1-5-vae
Base model
ACE-Step/Ace-Step1.5