How to use Efficient-Large-Model/Open-H3-Regenerate-2K with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Efficient-Large-Model/Open-H3-Regenerate-2K") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
it would be great if made a int8-convrot version of fast_h3_vae_noncausal_24l too :]
· Sign up or log in to comment
