theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

update Qwen-Image Quickstart

Browse Source
This commit is contained in:
Artiprocher
2025-08-29 14:09:49 +08:00
parent 4641d0f360
commit 6a46f32afe
4 changed files with 20 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -64,6 +64,7 @@ Details: [./examples/qwen_image/](./examples/qwen_image/)
```python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
pipe = QwenImagePipeline.from_pretrained(
@@ -77,7 +78,10 @@ pipe = QwenImagePipeline.from_pretrained(
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
prompt = "A detailed portrait of a girl underwater, wearing a blue flowing dress, hair gently floating, clear light and shadow, surrounded by bubbles, calm expression, fine details, dreamy and beautiful."
image = pipe(prompt, seed=0, num_inference_steps=40)
image = pipe(
prompt, seed=0, num_inference_steps=40,
# edit_image=Image.open("xxx.jpg").resize((1328, 1328)) # For Qwen-Image-Edit
)
image.save("image.jpg")
```

6
README_zh.md
View File

@@ -66,6 +66,7 @@ DiffSynth-Studio 为主流 Diffusion 模型（包括 FLUX、Wan 等）重新设
```python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
pipe = QwenImagePipeline.from_pretrained(
@@ -79,7 +80,10 @@ pipe = QwenImagePipeline.from_pretrained(
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
image = pipe(prompt, seed=0, num_inference_steps=40)
image = pipe(
prompt, seed=0, num_inference_steps=40,
# edit_image=Image.open("xxx.jpg").resize((1328, 1328)) # For Qwen-Image-Edit
)
image.save("image.jpg")
```

7
examples/qwen_image/README.md
View File

@@ -20,9 +20,9 @@ Run the following code to quickly load the [Qwen/Qwen-Image](https://www.modelsc
```python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
@@ -34,7 +34,10 @@ pipe = QwenImagePipeline.from_pretrained(
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
prompt = "A detailed portrait of a girl underwater, wearing a blue flowing dress, hair gently floating, clear light and shadow, surrounded by bubbles, calm expression, fine details, dreamy and beautiful."
image = pipe(prompt, seed=0, num_inference_steps=40)
image = pipe(
prompt, seed=0, num_inference_steps=40,
# edit_image=Image.open("xxx.jpg").resize((1328, 1328)) # For Qwen-Image-Edit
)
image.save("image.jpg")
```

7
examples/qwen_image/README_zh.md
View File

@@ -20,9 +20,9 @@ pip install -e .
```python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
@@ -34,7 +34,10 @@ pipe = QwenImagePipeline.from_pretrained(
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
image = pipe(prompt, seed=0, num_inference_steps=40)
image = pipe(
prompt, seed=0, num_inference_steps=40,
# edit_image=Image.open("xxx.jpg").resize((1328, 1328)) # For Qwen-Image-Edit
)
image.save("image.jpg")
```