import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Macro400K/macro-omnigen2-review", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]OmniGen2 checkpoint — anonymous review copy
This repository contains the checkpoint files needed by the anonymous review code. The model architecture and third-party licenses remain governed by their respective upstream projects.
Download with hf download Macro400K/macro-omnigen2-review --local-dir ckpts/Macro-OmniGen2.
See the anonymous code and project page for inference instructions.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support