Finegrain/refiners
1
0
Fork 0
mirror of https://github.com/finegrain-ai/refiners.git synced 2024-09-19 19:05:28 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

fix miscellaneous typos

Browse source
This commit is contained in:
Cédric Deltheil 2024-02-07 16:32:37 +00:00 committed by Cédric Deltheil
parent d7aadf99de
commit e36dda63fd
3 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/guides/adapting_sdxl/index.md
View file

@ -364,7 +364,7 @@ python scripts/conversion/convert_diffusers_ip_adapter.py --from ip-adapter-plus
This will download and convert both IP-Adapter and CLIP Image Encoder pretrained weights. This will download and convert both IP-Adapter and CLIP Image Encoder pretrained weights.
Then, in your Python code, simply instantiate a [`SDXLIPAdapter`][refiners.foundationals.latent_diffusion.stable_diffusion_xl.image_prompt.SDXLIPAdapter] targetting our `sdxl.unet`, and inject it using a simple `.inject()` call: Then, in your Python code, simply instantiate a [`SDXLIPAdapter`][refiners.foundationals.latent_diffusion.stable_diffusion_xl.image_prompt.SDXLIPAdapter] targeting our `sdxl.unet`, and inject it using a simple `.inject()` call:
```py ```py
# IP-Adapter # IP-Adapter

2
src/refiners/fluxion/layers/chain.py
View file

@ -55,7 +55,7 @@ class Chain(ContextModule):
This layer is the main building block of Fluxion. This layer is the main building block of Fluxion.
It is used to compose other layers in a sequential manner. It is used to compose other layers in a sequential manner.
Similary to [`torch.nn.Sequential`][torch.nn.Sequential], Similarly to [`torch.nn.Sequential`][torch.nn.Sequential],
it calls each of its sub-layers in order, chaining their outputs as inputs to the next sublayer. it calls each of its sub-layers in order, chaining their outputs as inputs to the next sublayer.
However, it also provides additional methods to manipulate its sub-layers and their context. However, it also provides additional methods to manipulate its sub-layers and their context.

4
src/refiners/foundationals/latent_diffusion/lora.py
View file

@ -131,7 +131,7 @@ class SDLoraManager:
SDLoraManager.auto_attach(unet_loras, self.unet, exclude=exclude) SDLoraManager.auto_attach(unet_loras, self.unet, exclude=exclude)
def remove_loras(self, *names: str) -> None: def remove_loras(self, *names: str) -> None:
"""Remove mulitple LoRAs from the target. """Remove multiple LoRAs from the target.
Args: Args:
names: The names of the LoRAs to remove. names: The names of the LoRAs to remove.
@ -179,7 +179,7 @@ class SDLoraManager:
self.update_scales({name: scale}) self.update_scales({name: scale})
def update_scales(self, scales: dict[str, float], /) -> None: def update_scales(self, scales: dict[str, float], /) -> None:
"""Update the scales of mulitple LoRAs. """Update the scales of multiple LoRAs.
Args: Args:
scales: The scales to update. scales: The scales to update.