How to use furaidosu/rtmi-zimage with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("furaidosu/rtmi-zimage") prompt = "Character portrait, chest-up. The background is plain white.A young adult human male character shown from the chest up, facing forward. The character is stylized and graphic.He has light-to-medium skin tone and medium-length black hair that falls around the sides of his face. He wears a colorful knit beanie with horizontal sections in red, yellow, blue, and a turquoise band around the forehead.His eyes are brown and slightly narrow, with a friendly expression. He has a thin mustache above his upper lip.His nose is rounded and centered. His mouth is openils open in a broad smile, showing only the upper teeth.He wears layered clothing a light-colored shirt underneath and a darker jacket or sweater over it, with visible stripes on the sleeves.Only the head, neck, shoulders, and upper torso are visible." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
