[Inference Providers] Support for LoRAs #3005
Merged
Conversation
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
Wauplin
reviewed
Apr 15, 2025
|
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. |
SBrandeis
added a commit
to huggingface/huggingface.js
that referenced
this pull request
Apr 25, 2025
) Following @Wauplin 's comment [here](huggingface/huggingface_hub#3005 (comment)) Pre-requisite: merge and deploy [this internal PR first](huggingface-internal/moon-landing#13498)
|
✅ I tested the PR with : from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
)
image = client.text_to_image(
prompt="a boy and a girl looking out of a window with a cat perched on the window sill",
model="openfree/flux-chatgpt-ghibli-lora",
)output image : |
Wauplin
approved these changes
Apr 29, 2025
Co-authored-by: Lucain <[email protected]>
Co-authored-by: Lucain <[email protected]>
Wauplin
approved these changes
Apr 29, 2025
|
i'm merging, CI is red for unrelated reasons (hub-ci seems to be down) |
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Outdated suggestions cannot be applied.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.
This work mirrors the PR in the js client (see huggingface.js#1347).
This PR introduces the support of LoRAs for fal-ai, this should not be merged until the server-side PR is merged (private).
Changes
_prepare_mapped_modelto return aProviderMappingInfoobject. This object returns the provider id, the hf model id (optional) and the lora weights path (optional) that is expected to be sent in the payload._prepare_payload_as_dictand_prepare_payload_as_bytessignatures to accept aProviderMappingInfoobject as an argument.the logic is implemented within the
TaskProviderHelperbase class, to avoid duplicating similar logic when we support LoRAs for the other providers. Note that LoRAs can also be used with other tasks liketext-to-videoas instance.