import torch
from diffsynth.core import ModelConfig
from diffsynth.pipelines.stable_diffusion import StableDiffusionPipeline

vram_config = {
    "offload_dtype": torch.float32,
    "offload_device": "cpu",
    "onload_dtype": torch.float32,
    "onload_device": "cpu",
    "preparing_dtype": torch.float32,
    "preparing_device": "cuda",
    "computation_dtype": torch.float32,
    "computation_device": "cuda",
}
pipe = StableDiffusionPipeline.from_pretrained(
    torch_dtype=torch.float32,
    model_configs=[
        ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="text_encoder/model.safetensors", **vram_config),
        ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="unet/diffusion_pytorch_model.safetensors", **vram_config),
        ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
    ],
    tokenizer_config=ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="tokenizer/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)

image = pipe(
    prompt="a photo of an astronaut riding a horse on mars, high quality, detailed",
    negative_prompt="blurry, low quality, deformed",
    cfg_scale=7.5,
    height=512,
    width=512,
    seed=42,
    rand_device="cuda",
    num_inference_steps=50,
)
image.save("image.jpg")