theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 09:28:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

update docs

Browse Source
This commit is contained in:
Artiprocher
2025-12-04 13:57:35 +08:00
parent 6fbd9e94ec
commit 17600eda0f
4 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docs/zh/Model_Details/Z-Image.md
View File

@@ -16,22 +16,32 @@ pip install -e .
## 快速开始
运行以下代码可以快速加载 [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) 模型并进行推理。
运行以下代码可以快速加载 [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) 模型并进行推理。FP8 精度量化会导致明显的图像质量劣化，因此不建议在 Z-Image Turbo 模型上开启任何量化，仅建议开启 CPU Offload，最低 8G 显存即可运行。
```python
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch
vram_config = {
"offload_dtype": torch.bfloat16,
"offload_device": "cpu",
"onload_dtype": torch.bfloat16,
"onload_device": "cpu",
"preparing_dtype": torch.bfloat16,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
pipe = ZImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.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"),
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors", **vram_config),
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors", **vram_config),
ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
image = pipe(prompt=prompt, seed=42, rand_device="cuda")