github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8212] Add "/v1/images/generations" endpoints for compatiblity in order to leverage vision models ` #5241

New Issue
Closed
opened 2026-04-12 16:23:00 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:23:00 -05:00
Owner
Copy Link

Originally created by @Routhinator on GitHub (Dec 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8212

I was playing with getting Nextcloud Assistant to try and use the llava model from the Ollama library, and realized that since Nextcloud's Asstant integration works through the LocalAI api syntax, it expects the vision models to respond from /v1/images/generations - which is an endpoint Ollama currently does not expose.

It would be nice to have this for integration compatibility.

Originally created by @Routhinator on GitHub (Dec 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8212 I was playing with getting Nextcloud Assistant to try and use the `llava` model from the Ollama library, and realized that since Nextcloud's Asstant integration works through the LocalAI api syntax, it expects the vision models to respond from `/v1/images/generations` - which is an endpoint Ollama currently does not expose. It would be nice to have this for integration compatibility.
GiteaMirror added the feature request label 2026-04-12 16:23:00 -05:00
GiteaMirror commented 2026-04-12 16:23:02 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 22, 2024):

ollama doesn't support image generation. #786, #8047

<!-- gh-comment-id:2558617039 --> @rick-github commented on GitHub (Dec 22, 2024): ollama doesn't support image generation. #786, #8047
GiteaMirror commented 2026-04-12 16:23:03 -05:00
Author
Owner
Copy Link

@Routhinator commented on GitHub (Dec 22, 2024):

Hmm ok that makes sense, guess maybe my best path, given I don't want a UI for a diffusion model, is to look at hosting a diffusion model on the same box and add it to the same nginx proxy with the /v1/images/ endpoints mapped to the diffusion api transparently.

Thanks.

<!-- gh-comment-id:2558631502 --> @Routhinator commented on GitHub (Dec 22, 2024): Hmm ok that makes sense, guess maybe my best path, given I don't want a UI for a diffusion model, is to look at hosting a diffusion model on the same box and add it to the same nginx proxy with the `/v1/images/` endpoints mapped to the diffusion api transparently. Thanks.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5241
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?