Update image generation demo README and parameters docs#4243
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates image generation documentation to reflect newer model deployment flows and LoRA parameter usage for OVMS demos and CLI reference.
Changes:
- Adds
--source_lorasto the image generation parameters table. - Reworks image generation demo deployment examples for
--source_model, pre-downloaded models, SDXL, and inpainting. - Updates LoRA demo examples with new model IDs, generation parameters, vector art example, and expected output images.
Reviewed changes
Copilot reviewed 2 out of 6 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
docs/parameters.md |
Documents the --source_loras image generation CLI parameter. |
demos/image_generation/README.md |
Updates image generation deployment and request examples, including SDXL, inpainting, and multi-LoRA workflows. |
dkalinowski
approved these changes
May 29, 2026
rasapala
approved these changes
May 29, 2026
dtrawins
reviewed
May 29, 2026
|
|
||
| :::: | ||
|
|
||
| > **NOTE:** The model directory must contain a valid `graph.pbtxt` file. This file is auto-generated when using `--pull` or `--source_model`. If you downloaded the model manually (e.g., via `huggingface-cli`), you can generate it by running `ovms --pull` with the same `--model_repository_path` and `--source_model` parameters, or create it manually — see [Image Generation calculator reference](../../docs/image_generation/reference.md) for all available options. |
Collaborator
There was a problem hiding this comment.
That is not the case anymore. It is possible to create graph in runtime with just model_path parameter
Collaborator
Author
There was a problem hiding this comment.
We may just have --task and model path.
atobiszei
added a commit
that referenced
this pull request
May 29, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
-> removed exporting models to make demos tests faster
-> added using
--cache_dirto speed up loading.-> added example images for LoRA's
http://openvino-doc.iotg.sclab.intel.com/atobisze_img_gen_demo_update/index.html