import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("deAPI-ai/acestep-1-5-xl-base-int8", 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 XL Base INT8
Open-source music generation. XL Base model (50 steps), higher quality and diversity. INT8 quantization for reduced memory usage.
Author
Quantization
Quantized by szwagros
License
MIT License
Hosted by deAPI-ai for use with GamerHash AI
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support