Finegrain/refiners
1
0
Fork 0
mirror of https://github.com/finegrain-ai/refiners.git synced 2024-11-12 16:18:22 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

clarify that add_lcm_lora can load SDXL-Lightning

Browse source
This commit is contained in:
Pierre Chapuis 2024-02-23 17:15:02 +01:00
parent 7e4e0f0650
commit 7f51d18045
1 changed files with 7 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
src/refiners/foundationals/latent_diffusion/stable_diffusion_xl/lcm_lora.py
View file

@ -26,23 +26,24 @@ def add_lcm_lora(
manager: SDLoraManager,
tensors: dict[str, torch.Tensor],
name: str = "lcm",
scale: float = 1.0 / 8.0,
scale: float = 8.0 / 64.0,
check_validity: bool = True,
) -> None:
"""Add a LCM LoRA to SDXLUNet.
"""Add a [LCM-LoRA](https://arxiv.org/abs/2311.05556) or a LoRA with similar structure
such as [SDXL-Lightning](https://arxiv.org/abs/2402.13929) to SDXLUNet.
This is a complex LoRA so [SDLoraManager.add_loras()][refiners.foundationals.latent_diffusion.lora.SDLoraManager.add_loras]
is not enough. Instead, we add the LoRAs to the UNet in several iterations, using the filtering mechanism of
[auto_attach_loras][refiners.fluxion.adapters.lora.auto_attach_loras].
This LoRA can be used with or without CFG in SD.
LCM-LoRA can be used with or without CFG in SD.
If you use CFG, typical values range from 1.0 (same as no CFG) to 2.0.
Args:
manager: A SDLoraManager for SDXL
tensors: The `state_dict` of the LCM LoRA
manager: A SDLoraManager for SDXL.
tensors: The `state_dict` of the LoRA.
name: The name of the LoRA.
scale: The scale to use for the LoRA (should generally not be changed).
scale: The scale to use for the LoRA (should generally not be changed, those LoRAs must use alpha / rank).
check_validity: Perform additional checks, raise an exception if they fail.
"""