Image-Text-to-Image
Diffusers
Safetensors
English
Chinese
QwenImageLayeredPipeline
quantized
qwen
8-bit precision
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("llmrobot/qwen-image-layered-int8-sdnq", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]8 bit (int8 with SVD rank 128) quantization of Qwen/Qwen-Image-Layered using SDNQ.
- Downloads last month
- 6