New Feature: ollama text-to-image support #13938

Activity

1. william (williamlzw)

   added the

   Feature

   issue type on Apr 30, 2026
2. Evan Mattson (moonbox3)

   added

   triage

   on Apr 30, 2026
3. Shoumik Chakravarty (shoumikchakravarty-dev)

   added a commit that references this issue on Sep 13, 2026

   Python: add Ollama text to image service

   ...

   This issue will close once commit eb89c99 is merged into the 'main' branch.

   eb89c99
4. shoumikchakravarty-dev commented on Sep 13, 2026

   

   Shoumik Chakravarty (shoumikchakravarty-dev)

   on Sep 13, 2026

   Last edited by shoumikchakravarty-dev

   More actions

   There us text-to-image Ollama API supports. Its implementable without new dependency. https://ollama.com/blog/image-generation. The scope should include to implement the generate_image to call Ollama API and base64 decode of the image content. Initial PR opened for this #14437
5. shoumikchakravarty-dev commented on Sep 24, 2026

   

   Shoumik Chakravarty (shoumikchakravarty-dev)

   on Sep 24, 2026

   More actions

   Evan Mattson (@moonbox3) - I have created the PR #14437 to address this issue. All test and quality checks pass; the only red check is the add_label job, which fails on every fork PR since #14411 (tracked in#14438, fix proposed in #14457). Could you take a look at the PR when you get a chance please?