mirror of
https://github.com/langgenius/dify-official-plugins.git
synced 2026-07-21 17:45:23 -04:00
aihubmix platform cannot add T2I AI models #600
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @lixc123 on GitHub (Aug 27, 2025).
Self Checks
Dify version
1.7.1
Plugin version
0.0.6
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
The aihubmix platform cannot add T2I AI models, such as gemini-2.5-flash-image-preview or imagen-4.0-fast-generate-001.
✔️ Error log
Credentials validation failed with status code 400
@dosubot[bot] commented on GitHub (Aug 27, 2025):
The reason you’re seeing “Credentials validation failed with status code 400” when trying to add T2I (Text-to-Image) models like gemini-2.5-flash-image-preview or imagen-4.0-fast-generate-001 to aihubmix is that T2I model support isn’t implemented in the current Dify or dify-official-plugins codebases. The backend only recognizes certain model types (LLM, text-embedding, rerank, speech2text, moderation, tts), and credential validation for unsupported types like T2I will always fail with a 400 error due to strict schema/type enforcement see codebase details.
This is a feature limitation, not a bug or misconfiguration. To enable T2I support, new provider/model files and updates to the ModelType enum, schema validation, and plugin logic would be needed plugin structure note.
For now, you can only add supported model types. If T2I support is critical for your workflow, you might want to track this as a feature request or consider contributing the necessary changes.
To reply, just mention @dosu.
How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other
