Hugging Peers

Z-Image-UIDesign-Fresh-Gradient-cd330f

☆ Save
by diffsynth-i2L-gallery Apache License 2.0
30 downloads 0 likes on ModelScope updated

Model card

UI设计、清新、渐变

模型介绍

本模型由模型 DiffSynth-Studio/ZImage-i2L-v2 生成

推理代码

安装 DiffSynth-Studio：

pip install diffsynth

开始推理：

from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch

pipe = ZImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="diffsynth-i2L-gallery/Z-Image-UIDesign-Fresh-Gradient-cd330f", origin_file_pattern="1782709415.718487-a514c23f-90f9-494a-a839-f40e010ef04f.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=50, cfg_scale=4)
image.save("image.jpg")