Update README.md (#3)
Browse files- Update README.md (6e059fd92d8dfd3cf97e5b23ef1f322500d43c02)
Co-authored-by: Kun Yan <[email protected]>
README.md
CHANGED
|
@@ -12,7 +12,7 @@ pipeline_tag: image-to-image
|
|
| 12 |
<p align="center">
|
| 13 |
💜 <a href="https://chat.qwen.ai/"><b>Qwen Chat</b></a>   |   🤗 <a href="https://huggingface.co/Qwen/Qwen-Image-Edit">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-Edit">ModelScope</a>   |    📑 <a href="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/Qwen_Image.pdf">Tech Report</a>    |    📑 <a href="https://qwenlm.github.io/blog/qwen-image-edit/">Blog</a>   
|
| 14 |
<br>
|
| 15 |
-
🖥️ <a href="https://huggingface.co/spaces/Qwen/
|
| 16 |
</p>
|
| 17 |
|
| 18 |
<p align="center">
|
|
@@ -73,47 +73,43 @@ with torch.inference_mode():
|
|
| 73 |
|
| 74 |
## Showcase
|
| 75 |
One of Qwen-Image-Edit’s standout capabilities is dual semantic and appearance editing. Semantic editing refers to modifying an image while preserving its original visual semantics. For instance, let’s start with Qwen’s mascot—Capibara:
|
| 76 |
-
, the character identity of Capibara remains consistent. This semantic editing capability enables effortless creation and modification of original IPs. For example, using a series of prompts, we expanded the set to create a full MBTI meme series:
|
| 78 |
-
|
| 81 |
Another key application of semantic editing is viewpoint transformation. As shown below, Qwen-Image-Edit can not only rotate objects by 90 degrees but even by 180 degrees, revealing the back of an object:
|
| 82 |
-
![Viewpoint transformation 90 degrees](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/
|
| 83 |
-
![Viewpoint transformation 180 degrees](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/
|
| 84 |
Another example of semantic editing is style transfer. Given a portrait, Qwen-Image-Edit can easily transform it into various styles such as Studio Ghibli, which is particularly useful for creating avatars or character IDs:
|
| 85 |
-
![Style transfer](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/
|
| 86 |
In addition to semantic editing, appearance editing addresses a different class of editing needs. Appearance editing requires certain regions of the image to remain completely unchanged. A common example is addition, deletion, or modification.
|
| 87 |
Below, we demonstrate adding a signboard to an image. Notably, Qwen-Image-Edit not only adds the signboard but also generates a corresponding reflection:
|
| 88 |
-
![Adding a signboard](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/
|
| 89 |
Here’s another interesting example—removing fine strands of hair:
|
| 90 |
-
![Removing fine strands of hair](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/
|
| 91 |
Below shows how to modify the color of text in an image—changing the color of the letter "n" to blue:
|
| 92 |
-
|
| 99 |
The second hallmark of Qwen-Image-Edit is its accurate text editing, made possible by Qwen-Image’s powerful text rendering capabilities.
|
| 100 |
For example, the following two images demonstrate Qwen-Image-Edit’s ability in editing English text:
|
| 101 |
-
!
|
| 118 |
In summary, we hope Qwen-Image-Edit will further advance the field of image generation, significantly lower the technical barriers to visual content creation, and inspire even more innovative applications.
|
| 119 |
|
|
|
|
| 12 |
<p align="center">
|
| 13 |
💜 <a href="https://chat.qwen.ai/"><b>Qwen Chat</b></a>   |   🤗 <a href="https://huggingface.co/Qwen/Qwen-Image-Edit">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-Edit">ModelScope</a>   |    📑 <a href="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/Qwen_Image.pdf">Tech Report</a>    |    📑 <a href="https://qwenlm.github.io/blog/qwen-image-edit/">Blog</a>   
|
| 14 |
<br>
|
| 15 |
+
🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-Edit">Demo</a>   |   💬 <a href="https://github.com/QwenLM/Qwen-Image/blob/main/assets/wechat.png">WeChat (微信)</a>   |   🫨 <a href="https://discord.gg/CV4E9rpNSD">Discord</a>  |    <a href="https://github.com/QwenLM/Qwen-Image">Github</a>  
|
| 16 |
</p>
|
| 17 |
|
| 18 |
<p align="center">
|
|
|
|
| 73 |
|
| 74 |
## Showcase
|
| 75 |
One of Qwen-Image-Edit’s standout capabilities is dual semantic and appearance editing. Semantic editing refers to modifying an image while preserving its original visual semantics. For instance, let’s start with Qwen’s mascot—Capibara:
|
| 76 |
+
|
| 77 |
Although every pixel in the edited image differs from the input (the leftmost image), the character identity of Capibara remains consistent. This semantic editing capability enables effortless creation and modification of original IPs. For example, using a series of prompts, we expanded the set to create a full MBTI meme series:
|
| 78 |
+
|
|
|
|
|
|
|
| 79 |
Another key application of semantic editing is viewpoint transformation. As shown below, Qwen-Image-Edit can not only rotate objects by 90 degrees but even by 180 degrees, revealing the back of an object:
|
| 80 |
+
|
| 81 |
+
|
| 82 |
Another example of semantic editing is style transfer. Given a portrait, Qwen-Image-Edit can easily transform it into various styles such as Studio Ghibli, which is particularly useful for creating avatars or character IDs:
|
| 83 |
+
|
| 84 |
In addition to semantic editing, appearance editing addresses a different class of editing needs. Appearance editing requires certain regions of the image to remain completely unchanged. A common example is addition, deletion, or modification.
|
| 85 |
Below, we demonstrate adding a signboard to an image. Notably, Qwen-Image-Edit not only adds the signboard but also generates a corresponding reflection:
|
| 86 |
+
|
| 87 |
Here’s another interesting example—removing fine strands of hair:
|
| 88 |
+
|
| 89 |
Below shows how to modify the color of text in an image—changing the color of the letter "n" to blue:
|
| 90 |
+
|
| 91 |
Appearance editing is also crucial in modifying human poses, backgrounds, and clothing, as demonstrated in the following three images:
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
|
|
|
|
|
|
|
| 95 |
The second hallmark of Qwen-Image-Edit is its accurate text editing, made possible by Qwen-Image’s powerful text rendering capabilities.
|
| 96 |
For example, the following two images demonstrate Qwen-Image-Edit’s ability in editing English text:
|
| 97 |
+
|
| 98 |
+
|
| 99 |
Qwen-Image-Edit can also edit Chinese posters—modifying both large and small text elements:
|
| 100 |
+
|
| 101 |
Finally, let’s walk through a concrete example showing how sequential editing can correct errors in a calligraphy artwork originally generated by Qwen-Image:
|
| 102 |
+
|
| 103 |
This artwork contains several incorrect characters. We can progressively correct them using Qwen-Image-Edit. For instance, we can add bounding boxes directly on the original image and instruct Qwen-Image-Edit to fix the highlighted parts—here, correcting “稽” within the red box and “亭” within the blue box:
|
| 104 |
+
|
| 105 |
Unfortunately, the character “稽” is uncommon, and the model initially fails to correct it—the lower-right component should be “旨”, not “日”. We can further highlight the incorrect “日” with a red box and prompt Qwen-Image-Edit to fine-tune that region into “旨”:
|
| 106 |
+
|
| 107 |
Amazing, right? Following this iterative approach, we can progressively correct all errors until reaching the final version:
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
|
| 113 |
Ultimately, we obtain a fully correct calligraphy version of Lantingji Xu (Preface to the Poems Composed at the Orchid Pavilion)!
|
| 114 |
In summary, we hope Qwen-Image-Edit will further advance the field of image generation, significantly lower the technical barriers to visual content creation, and inspire even more innovative applications.
|
| 115 |
|