Skip to content

[LoRA] support lightx2v lora in wan #12040

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Aug 2, 2025
+10 −0
Merged

[LoRA] support lightx2v lora in wan #12040

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
cd730e7
support lightx2v lora in wan
sayakpaul Aug 1, 2025
0b0f311
Merge branch 'main' into support-lighttx2v-lora
sayakpaul Aug 1, 2025
7308bc1
add docsa.
sayakpaul Aug 1, 2025
7a30014
reviewer feedback
sayakpaul Aug 2, 2025
7f0638a
empty
sayakpaul Aug 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions docs/source/en/api/pipelines/wan.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,12 @@ The following Wan models are supported in Diffusers:
- [Wan 2.1 VACE 1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B-diffusers)
- [Wan 2.1 VACE 14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers)

Follow Wan 2.2 checkpoints are also supported:

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's just continue growing the above list instead of adding another

- [Wan 2.2 T2V 14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers)
- [Wan 2.2 I2V 14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers)
- [Wan 2.2 TI2V 5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers)

> [!TIP]
> Click on the Wan2.1 models in the right sidebar for more examples of video generation.

Expand Down Expand Up @@ -327,6 +333,10 @@ The general rule of thumb to keep in mind when preparing inputs for the VACE pip

- Try lower `shift` values (`2.0` to `5.0`) for lower resolution videos and higher `shift` values (`7.0` to `12.0`) for higher resolution images.

## Using LightX2V LoRAs
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's put this in the Notes section instead of creating a new subsection


Wan 2.1 and 2.2 support using [LightX2V LoRAs](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v) to speed up inference. Using them on Wan 2.2 is slightly more involed. Refer to [this code snippet](https://github.com/huggingface/diffusers/pull/12040#issuecomment-3144185272) to learn more.

## WanPipeline

[[autodoc]] WanPipeline
Expand Down
4 changes: 4 additions & 0 deletions src/diffusers/loaders/lora_conversion_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1974,6 +1974,10 @@ def _convert_non_diffusers_wan_lora_to_diffusers(state_dict):
converted_key = f"condition_embedder.image_embedder.{img_ours}.lora_B.weight"
if original_key in original_state_dict:
converted_state_dict[converted_key] = original_state_dict.pop(original_key)
bias_key_theirs = original_key.removesuffix(f".{lora_up_key}.weight") + ".diff_b"
if bias_key_theirs in original_state_dict:
bias_key = converted_key.removesuffix(".weight") + ".bias"
converted_state_dict[bias_key] = original_state_dict.pop(bias_key_theirs)

if len(original_state_dict) > 0:
diff = all(".diff" in k for k in original_state_dict)
Expand Down
Loading