Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitd21d1aa

Browse files
committed
update docs
1 parent7519e2f commitd21d1aa

File tree

3 files changed

+26
-0
lines changed

3 files changed

+26
-0
lines changed

‎README.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@ API and command-line option may change frequently.***
2121
-[SD3/SD3.5](./docs/sd3.md)
2222
-[Flux-dev/Flux-schnell](./docs/flux.md)
2323
-[Chroma](./docs/chroma.md)
24+
-[Qwen Image](./docs/qwen_image.md)
2425
- Image Edit Models
2526
-[FLUX.1-Kontext-dev](./docs/kontext.md)
2627
- Video Models
@@ -296,6 +297,7 @@ arguments:
296297
--clip_g path to the clip-g text encoder
297298
--clip_vision path to the clip-vision encoder
298299
--t5xxl path to the t5xxl text encoder
300+
--qwen2vl path to the qwen2vl text encoder
299301
--vae [VAE] path to vae
300302
--taesd [TAESD_PATH] path to taesd. Using Tiny AutoEncoder for fast decoding (low quality)
301303
--control-net [CONTROL_PATH] path to control net model
@@ -464,6 +466,7 @@ Thank you to all the people who have already contributed to stable-diffusion.cpp
464466
## References
465467
466468
- [ggml](https://github.com/ggerganov/ggml)
469+
- [diffusers](https://github.com/huggingface/diffusers)
467470
- [stable-diffusion](https://github.com/CompVis/stable-diffusion)
468471
- [sd3-ref](https://github.com/Stability-AI/sd3-ref)
469472
- [stable-diffusion-stability-ai](https://github.com/Stability-AI/stablediffusion)

‎assets/qwen/example.png‎

1.35 MB
Loading

‎docs/qwen_image.md‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
#How to Use
2+
3+
##Download weights
4+
5+
- Download Qwen Image
6+
- safetensors:https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/diffusion_models
7+
- gguf:https://huggingface.co/QuantStack/Qwen-Image-GGUF/tree/main
8+
- Download vae
9+
- safetensors:https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae
10+
- Download qwen_2.5_vl 7b
11+
- safetensors:https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders
12+
- gguf:https://huggingface.co/mradermacher/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
13+
14+
##Examples
15+
16+
```
17+
.\bin\Release\sd.exe --diffusion-model ..\..\ComfyUI\models\diffusion_models\qwen-image-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\qwen_image_vae.safetensors --qwen2vl ..\..\ComfyUI\models\text_encoders\Qwen2.5-VL-7B-Instruct-Q8_0.gguf -p '一个穿着"QWEN"标志的T恤的中国美女正拿着黑色的马克笔面相镜头微笑。她身后的玻璃板上手写体写着 “一、Qwen-Image的技术路线： 探索视觉生成基础模型的极限，开创理解与生成一体化的未来。二、Qwen-Image的模型特色：1、复杂文字渲染。支持中英渲染、自动布局； 2、精准图像编辑。支持文字编辑、物体增减、风格变换。三、Qwen-Image的未来愿景：赋能专业内容创作、助力生成式AI发展。”' --cfg-scale 2.5 --sampling-method euler -v --offload-to-cpu -H 1024 -W 1024 --diffusion-fa --flow-shift 3
18+
```
19+
20+
<imgalt="qwen example"src="../assets/qwen/example.png" />
21+
22+
23+

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp