import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("vladmandic/HiDream-O1-Image-Dev-SDNQ-8bit-dynamic", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Prequantized version of https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev using SDNQ SVD+Dynamic in INT8 precision
- Downloads last month
- 6
Model tree for vladmandic/HiDream-O1-Image-Dev-SDNQ-8bit-dynamic
Base model
HiDream-ai/HiDream-O1-Image-Dev