theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-21 08:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

support z-image-omni-base

Browse Source
This commit is contained in:
Artiprocher
2026-01-05 14:03:15 +08:00
parent ab8580f77e
commit 63559a3ad6
5 changed files with 948 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
examples/z_image/model_inference/Z-Image-Omni-Base.py Normal file
View File

@@ -0,0 +1,23 @@
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
from PIL import Image
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-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/"),
)
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=0, num_inference_steps=40, cfg_scale=4)
image.save("image_Z-Image-Omni-Base.jpg")
image = Image.open("image_Z-Image-Omni-Base.jpg")
prompt = "Change the women's clothes to white cheongsam, keep other content unchanged"
image = pipe(prompt=prompt, edit_image=image, seed=42, rand_device="cuda", num_inference_steps=40, cfg_scale=4)
image.save("image_edit_Z-Image-Omni-Base.jpg")