测试lora

模型介绍

本模型依托魔搭社区（ModelScope）AIGC专区模型训练环境与算力完成训练。

• 模型类型：LoRA
• 基础模型：Qwen/Qwen-Image-2512
• 训练代码：DiffSynth-Studio
• 训练数据量：45
• 总训练步数：6000
• 开源协议：Apache-2.0

推理代码

安装 DiffSynth-Studio：

pip install diffsynth

开始推理：

from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch

pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="zhang9863/test_lora", origin_file_pattern="test_lora_c1-st6000.safetensors"))
prompt = "a cat"
image = pipe(prompt)
image.save("image.jpg")