Instructions to use mdmachine/ACEStep-XL-Regrind-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mdmachine/ACEStep-XL-Regrind-V1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ACE-Step/acestep-v15-xl-turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("mdmachine/ACEStep-XL-Regrind-V1") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/ComfyUI_temp_pugkg_00088_.png | |
| text: '-' | |
| base_model: ACE-Step/acestep-v15-xl-turbo | |
| instance_prompt: null | |
| license: cc-by-nc-sa-4.0 | |
| # ACEStep XL Regrind V1 | |
| <Gallery /> | |
| ## Model description | |
| Three-file resonance suppression package for ACE-Step XL Turbo. Reduces harmonic hum and resonance accumulation in long generations (60s+). Includes baked base model, VAE decoder regrind, and LoRA adapter. | |
| ## Download model | |
| [Download](/mdmachine/ACEStep-XL-Regrind-V1/tree/main) them in the Files & versions tab. | |