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 #8047] Can add Stable Diffusion 3.5 model？ #67202

New Issue
Closed
opened 2026-05-04 09:36:48 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 09:36:48 -05:00
Owner
Copy Link

Originally created by @dmmhk on GitHub (Dec 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8047

Cannot find Diffusion 3.5 model on the ollama platform?Does Olama not support the Diffusion 3.5 model? Can we add an Diffusion 3.5 model?
Implementing text and image generation using API+JSON+Base64+Prompt。

Originally created by @dmmhk on GitHub (Dec 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8047 Cannot find Diffusion 3.5 model on the ollama platform?Does Olama not support the Diffusion 3.5 model? Can we add an Diffusion 3.5 model? Implementing text and image generation using API+JSON+Base64+Prompt。
GiteaMirror added the model label 2026-05-04 09:36:48 -05:00
GiteaMirror commented 2026-05-04 09:36:49 -05:00
Author
Owner
Copy Link

@Salpingopharyngeus commented on GitHub (Dec 12, 2024):

Short answer is no, you shouldn't be able to as Ollama is dedicated to Large LANGUAGE models.

Longer answer is that in general, Stable diffusion and Large Language Models require different architectures, and while some llava models (and more recently Llama models) do have the ability to reason about images, being able to identify an image / the contents of an image is inherently different from being able to generate one, and ollama isn't designed or equiped for that.

As a real life example, if you give me a picture of a flower, and ask me to write a poem or tell you about the flower, with sufficent training or knowledge I could probably do that-but that doesn't necessary mean I could then draw the flower, or visualize let alone draw that flower given a text description. To successfully execute that drawing task, I'd probably need training of some sort.

For stable diffusion you should be looking into something like Automatic1111, forge, comfy, or swarm (to name a few of the more popular projects).

<!-- gh-comment-id:2537484338 --> @Salpingopharyngeus commented on GitHub (Dec 12, 2024): Short answer is no, you shouldn't be able to as Ollama is dedicated to Large **LANGUAGE** models. Longer answer is that in general, Stable diffusion and Large Language Models require different architectures, and while some llava models (and more recently Llama models) do have the ability to reason about images, being able to identify an image / the contents of an image is inherently different from being able to generate one, and ollama isn't designed or equiped for that. As a real life example, if you give me a picture of a flower, and ask me to write a poem or tell you about the flower, with sufficent training or knowledge I could probably do that-but that doesn't necessary mean I could then draw the flower, or visualize let alone draw that flower given a text description. To successfully execute that drawing task, I'd probably need training of some sort. For stable diffusion you should be looking into something like Automatic1111, forge, comfy, or swarm (to name a few of the more popular projects).
GiteaMirror commented 2026-05-04 09:36:50 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 23, 2024):

Merging with https://github.com/ollama/ollama/issues/786

<!-- gh-comment-id:2558702147 --> @jmorganca commented on GitHub (Dec 23, 2024): Merging with https://github.com/ollama/ollama/issues/786
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 model
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#67202
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?