Skip to content

Conversation

hanouticelina
Copy link
Contributor

Fixes #3398.
based on fal-ai input schema, the target size should be sent via image_size. Some models/providers may ignore this parameter if it isn't supported (updated the docstring accordingly).

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@hanouticelina hanouticelina merged commit 88c5f09 into main Sep 29, 2025
25 of 26 checks passed
@hanouticelina hanouticelina deleted the fix-fal-image-to-image-target-size branch September 29, 2025 13:57
hanouticelina added a commit that referenced this pull request Sep 29, 2025
)

* fix target size mapping for image-to-image fal-ai

* docs

* docstring
hanouticelina added a commit to huggingface/huggingface.js that referenced this pull request Oct 7, 2025
Related to huggingface/huggingface_hub#3399,
some providers or models may ignore this parameter if it's not
supported. This PR updates the docstring to make that clearer and align
it with the one in `huggingface_hub`.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Target_size issue in image to image inference

3 participants