AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[Chore] add LoraLoaderMixin to the inits (#8981)

Browse Source 
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

* loraloadermixin.

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
This commit is contained in:
Sayak Paul
2024-07-26 08:59:33 +05:30
committed by GitHub
parent 50e66f2f95
commit d87fe95f90
105 changed files with 3079 additions and 2160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/source/en/using-diffusers/inference_with_lcm.md
View File

@@ -64,7 +64,7 @@ image
</hfoption>
<hfoption id="LCM-LoRA">
To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
A couple of notes to keep in mind when using LCM-LoRAs are:
@@ -156,7 +156,7 @@ image
</hfoption>
<hfoption id="LCM-LoRA">
To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
> [!TIP]
> Experiment with different values for `num_inference_steps`, `strength`, and `guidance_scale` to get the best results.
@@ -207,7 +207,7 @@ image
## Inpainting
To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
```py
import torch
@@ -262,7 +262,7 @@ LCMs are compatible with adapters like LoRA, ControlNet, T2I-Adapter, and Animat
<hfoptions id="lcm-lora">
<hfoption id="LCM">
Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
```python
from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, LCMScheduler
@@ -294,7 +294,7 @@ image
</hfoption>
<hfoption id="LCM-LoRA">
Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
```py
import torch
@@ -389,7 +389,7 @@ make_image_grid([canny_image, image], rows=1, cols=2)
</hfoption>
<hfoption id="LCM-LoRA">
Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
> [!TIP]
> Experiment with different values for `num_inference_steps`, `controlnet_conditioning_scale`, `cross_attention_kwargs`, and `guidance_scale` to get the best results.
@@ -525,7 +525,7 @@ image = pipe(
</hfoption>
<hfoption id="LCM-LoRA">
Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
```py
import torch

16
docs/source/en/using-diffusers/loading_adapters.md
View File

@@ -116,7 +116,7 @@ import torch
pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
```
Then use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
Then use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
```py
pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora", weight_name="cereal_box_sdxl_v1.safetensors")
@@ -129,7 +129,7 @@ image
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_lora.png" />
</div>
The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
- the LoRA weights don't have separate identifiers for the UNet and text encoder
- the LoRA weights have separate identifiers for the UNet and text encoder
@@ -153,7 +153,7 @@ image
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
</div>
To unload the LoRA weights, use the [`~loaders.LoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
To unload the LoRA weights, use the [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
```py
pipeline.unload_lora_weights()
@@ -161,9 +161,9 @@ pipeline.unload_lora_weights()
### Adjust LoRA weight scale
For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
For both [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.LoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
```python
pipe = ... # create pipeline
pipe.load_lora_weights(..., adapter_name="my_adapter")
@@ -186,7 +186,7 @@ This also works with multiple adapters - see [this guide](https://huggingface.co
<Tip warning={true}>
Currently, [`~loaders.LoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
Currently, [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
</Tip>
@@ -203,7 +203,7 @@ To load a Kohya LoRA, let's download the [Blueprintify SD XL 1.0](https://civita
!wget https://civitai.com/api/download/models/168776 -O blueprintify-sd-xl-10.safetensors
```
Load the LoRA checkpoint with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
Load the LoRA checkpoint with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
```py
from diffusers import AutoPipelineForText2Image
@@ -227,7 +227,7 @@ image
Some limitations of using Kohya LoRAs with 🤗 Diffusers include:
- Images may not look like those generated by UIs - like ComfyUI - for multiple reasons, which are explained [here](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736).
- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
</Tip>

14
docs/source/en/using-diffusers/merge_loras.md
View File

@@ -14,9 +14,9 @@ specific language governing permissions and limitations under the License.
It can be fun and creative to use multiple [LoRAs]((https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora)) together to generate something entirely new and unique. This works by merging multiple LoRA weights together to produce images that are a blend of different styles. Diffusers provides a few methods to merge LoRAs depending on *how* you want to merge their weights, which can affect image quality.
This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.LoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
```py
from diffusers import DiffusionPipeline
@@ -182,9 +182,9 @@ image
## fuse_lora
Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.LoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.LoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
For example, if you have a base model and adapters loaded and set as active with the following adapter weights:
@@ -199,13 +199,13 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
```
Fuse these LoRAs into the UNet with the [`~loaders.LoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.LoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
Fuse these LoRAs into the UNet with the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
```py
pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
```
Then you should use [`~loaders.LoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
Then you should use [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
```py
pipeline.unload_lora_weights()
@@ -226,7 +226,7 @@ image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai"
image
```
You can call [`~loaders.LoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
You can call [`~loaders.StableDiffusionLoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
```py
pipeline.unfuse_lora()

2
docs/source/en/using-diffusers/other-formats.md
View File

@@ -74,7 +74,7 @@ pipeline = StableDiffusionPipeline.from_single_file(
[LoRA](https://hf.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) is a lightweight adapter that is fast and easy to train, making them especially popular for generating images in a certain way or style. These adapters are commonly stored in a safetensors file, and are widely popular on model sharing platforms like [civitai](https://civitai.com/).
LoRAs are loaded into a base model with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method.
LoRAs are loaded into a base model with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method.
```py
from diffusers import StableDiffusionXLPipeline