mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-23 09:28:12 +00:00
22 lines
1.1 KiB
Python
22 lines
1.1 KiB
Python
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
|
|
from diffsynth.core import load_state_dict
|
|
import torch
|
|
|
|
|
|
pipe = ZImagePipeline.from_pretrained(
|
|
torch_dtype=torch.bfloat16,
|
|
device="cuda",
|
|
model_configs=[
|
|
ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="transformer/*.safetensors"),
|
|
ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="siglip/model.safetensors"),
|
|
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
|
|
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
|
|
],
|
|
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
|
|
)
|
|
state_dict = load_state_dict("./models/train/Z-Image-Omni-Base_full/epoch-1.safetensors", torch_dtype=torch.bfloat16)
|
|
pipe.dit.load_state_dict(state_dict)
|
|
prompt = "a dog"
|
|
image = pipe(prompt=prompt, seed=42, rand_device="cuda", num_inference_steps=40, cfg_scale=4)
|
|
image.save("image.jpg")
|