from diffsynth.pipelines.moss_image import MOSSImagePipeline, ModelConfig import torch pipe = MOSSImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"), ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors"), ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", computation_dtype=torch.float32), ], tokenizer_config=ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="tokenizer/"), ) prompt = '''A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese: "记得买牛奶和鸡蛋! 牛奶两盒,鸡蛋一打。 顺便带一袋面包。"''' image = pipe(prompt, height=1024, width=1024, seed=42, num_inference_steps=50, cfg_scale=3.0) image.save("image_MOSS-Image-SFT.jpg")