[docs] LTX-2.5 Modular Pipeline Docs - #14450
Conversation
github-actions
Bot
added
size/M
|
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. |
| cm = ComponentsManager() | ||
| pipe = ModularPipeline.from_pretrained(model_path, components_manager=cm) | ||
| pipe.load_components(dtype=torch.bfloat16) | ||
| if getattr(pipe, "prompt_enhancer", None) is None: |
There was a problem hiding this comment.
ohh should we know if it's None or not
There was a problem hiding this comment.
you should update it to point out the correct repo https://huggingface.co/Lightricks/LTX-2.5-Diffusers/blob/main/modular_model_index.json#L79
(please test it out and then maybe PR into their repo)
There was a problem hiding this comment.
I have opened a PR to add the prompt_enhancer and processor to Lightricks/LTX-2.5-Diffusers at https://huggingface.co/Lightricks/LTX-2.5-Diffusers/discussions/13.
There was a problem hiding this comment.
can you update the example now?
…ownloads the Gemma 4 prompt enhancer and processor
|
|
||
| ```py | ||
| import torch | ||
| from transformers import AutoModelForImageTextToText, AutoProcessor |
There was a problem hiding this comment.
can remove these as they're not used (same for the snippet below)
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
4 participants
What does this PR do?
This PR documents the LTX-2.5 modular pipeline introduced in #14447.
Before submitting
self-reviewskill on the diff?documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@yiyixuxu
@sayakpaul
@stevhliu