-
-
Notifications
You must be signed in to change notification settings - Fork 13.5k
๐ style: support more Text2Image from Qwen #8574
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. Weโll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@hezhijie0327 is attempting to deploy a commit to the LobeHub Community Team on Vercel. A member of the Team first needs to authorize it. |
Reviewer's GuideThis PR enriches the Qwen image model registry by adding missing Text2Image variants for Ali Bailing and several open-source models, refines display names and descriptions, and refactors the API endpoint resolution for image generation to a dynamic approach based on model prefixes. Class diagram for dynamic Qwen image endpoint resolutionclassDiagram
class QwenText2ImageModels {
+string[] (model prefixes)
}
class createImageTask {
+async createImageTask(payload, apiKey): Promise<string>
}
class getModelType {
+getModelType(model: string): string
}
QwenText2ImageModels <.. getModelType : uses
getModelType <.. createImageTask : calls
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
๐ @hezhijie0327 Thank you for raising your pull request and contributing to our Community |
TestGru AssignmentSummary
Tip You can |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey @hezhijie0327 - I've reviewed your changes and they look great!
Help me be more useful! Please click ๐ or ๐ on each comment and I'll use the feedback to improve your reviews.
Codecov Reportโ
All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #8574 +/- ##
===========================================
+ Coverage 85.58% 96.26% +10.67%
===========================================
Files 910 17 -893
Lines 69093 2917 -66176
Branches 4530 283 -4247
===========================================
- Hits 59134 2808 -56326
+ Misses 9959 109 -9850
Flags with carried forward coverage won't be shown. Click here to find out more. โ View full report in Codecov by Sentry. ๐ New features to boost your workflow:
|
@hezhijie0327 ๆจกๅ็้กบๅบไธ๏ผๅ็ณปๅ๏ผๅฏ่ฝๆไพฟๅฎ็ๆพๅ้ขๅฅฝไธไบ๏ผๆไปฅ wanxiang turbo ๆพ plus ๅ้ขๅฅฝ็น |
@hezhijie0327 In the order of the model, in the same series, it may be better to put the cheaper ones in front, so wanxiang turbo put the plus ones in front |
ๅฅฝไบ ๅ ถไป็ๅฎ็ฝๆๆถ้ฝๆฏๅ ่ดน็ ๅฐฑๆ็ งๆจกๅ็ๆฌๅๆๆกฃ้กบๅบๆๅบไบ |
OK, other official websites are free for the time being, so they are sorted in the order of model version and document |
The latest updates on your projects. Learn more about Vercel for Git โ๏ธ
|
โค๏ธ Great PR @hezhijie0327 โค๏ธ The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world. |
### [Version 1.105.1](v1.105.0...v1.105.1) <sup>Released on **2025-07-29**</sup> #### ๐ Styles - **misc**: Support more Text2Image from Qwen. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Support more Text2Image from Qwen, closes [#8574](#8574) ([b8c0e2d](b8c0e2d)) </details> <div align="right"> [](#readme-top) </div>
๐ This PR is included in version 1.105.1 ๐ The release is available on: Your semantic-release bot ๐ฆ๐ |
### [Version 1.104.1](v1.104.0...v1.104.1) <sup>Released on **2025-07-29**</sup> #### โป Code Refactoring - **misc**: Clean mcp sitemap, refactor jose-JWT to xor obfuscation. #### ๐ Styles - **misc**: Add more OpenAI SDK Text2Image providers, support more Text2Image from Qwen, update i18n. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Clean mcp sitemap, closes [lobehub#8596](https://github.com/jaworldwideorg/OneJA-Bot/issues/8596) ([b9e3e66](b9e3e66)) * **misc**: Refactor jose-JWT to xor obfuscation, closes [lobehub#8595](https://github.com/jaworldwideorg/OneJA-Bot/issues/8595) ([be98d56](be98d56)) #### Styles * **misc**: Add more OpenAI SDK Text2Image providers, closes [lobehub#8573](https://github.com/jaworldwideorg/OneJA-Bot/issues/8573) ([403aebd](403aebd)) * **misc**: Support more Text2Image from Qwen, closes [lobehub#8574](https://github.com/jaworldwideorg/OneJA-Bot/issues/8574) ([b8c0e2d](b8c0e2d)) * **misc**: Update i18n, closes [lobehub#8593](https://github.com/jaworldwideorg/OneJA-Bot/issues/8593) ([356cf0c](356cf0c)) </details> <div align="right"> [](#readme-top) </div>
### [Version 1.105.1](lobehub/lobe-chat@v1.105.0...v1.105.1) <sup>Released on **2025-07-29**</sup> #### ๐ Styles - **misc**: Support more Text2Image from Qwen. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Support more Text2Image from Qwen, closes [lobehub#8574](lobehub#8574) ([5b0fbc9](lobehub@5b0fbc9)) </details> <div align="right"> [](#readme-top) </div>
### [Version 1.105.1](lobehub/lobe-chat@v1.105.0...v1.105.1) <sup>Released on **2025-07-29**</sup> #### ๐ Styles - **misc**: Support more Text2Image from Qwen. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Support more Text2Image from Qwen, closes [lobehub#8574](lobehub#8574) ([b8c0e2d](lobehub@b8c0e2d)) </details> <div align="right"> [](#readme-top) </div>
๐ป ๅๆด็ฑปๅ | Change Type
๐ ๅๆด่ฏดๆ | Description of Change
text2image
Note:
wan2.2-t2i-flash
wan2.2-t2i-plus
wanx2.1-t2i-plus
wanx2.1-t2i-turbo
wanx2.0-t2i-turbo
wanx-v1
flux-schnell
flux-dev
flux-merged
๐ ่กฅๅ ไฟกๆฏ | Additional Information
Summary by Sourcery
Add a comprehensive set of new Qwen text-to-image model configurations and improve the image task creation logic by dynamically determining the endpoint path based on model type
New Features:
Enhancements: