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

Rename (#4294)

Browse Source 
* up

* Apply suggestions from code review

* Apply suggestions from code review

* up
This commit is contained in:
Patrick von Platen
2023-07-26 20:41:21 +02:00
committed by GitHub
parent b83bdce42a
commit 6a6dfe1cbd
9 changed files with 31 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_xl.md
View File

@@ -26,8 +26,8 @@ The abstract of the paper is the following:
### Available checkpoints:
- *Text-to-Image (1024x1024 resolution)*: [stabilityai/stable-diffusion-xl-base-0.9](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9) with [`StableDiffusionXLPipeline`]
- *Image-to-Image / Refiner (1024x1024 resolution)*: [stabilityai/stable-diffusion-xl-refiner-0.9](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9) with [`StableDiffusionXLImg2ImgPipeline`]
- *Text-to-Image (1024x1024 resolution)*: [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) with [`StableDiffusionXLPipeline`]
- *Image-to-Image / Refiner (1024x1024 resolution)*: [stabilityai/stable-diffusion-xl-refiner-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0) with [`StableDiffusionXLImg2ImgPipeline`]
## Usage Example
@@ -50,7 +50,7 @@ from diffusers import StableDiffusionXLPipeline
import torch
pipe = StableDiffusionXLPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
@@ -68,7 +68,7 @@ from diffusers import StableDiffusionXLImg2ImgPipeline
from diffusers.utils import load_image
pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-refiner-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe = pipe.to("cuda")
url = "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png"
@@ -88,7 +88,7 @@ from diffusers import StableDiffusionXLInpaintPipeline
from diffusers.utils import load_image
pipe = StableDiffusionXLInpaintPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
@@ -104,8 +104,8 @@ image = pipe(prompt=prompt, image=init_image, mask_image=mask_image, num_inferen
### Refining the image output
In addition to the [base model checkpoint](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9),
StableDiffusion-XL also includes a [refiner checkpoint](huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9)
In addition to the [base model checkpoint](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0),
StableDiffusion-XL also includes a [refiner checkpoint](huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0)
that is specialized in denoising low-noise stage images to generate images of improved high-frequency quality.
This refiner checkpoint can be used as a "second-step" pipeline after having run the base checkpoint to improve
image quality.
@@ -149,12 +149,12 @@ from diffusers import DiffusionPipeline
import torch
base = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
refiner = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-refiner-0.9",
"stabilityai/stable-diffusion-xl-refiner-1.0",
text_encoder_2=base.text_encoder_2,
vae=base.vae,
torch_dtype=torch.float16,
@@ -219,7 +219,7 @@ The ensemble-of-experts method works well on all available schedulers!
#### 2.) Refining the image output from fully denoised base image
In standard [`StableDiffusionImg2ImgPipeline`]-fashion, the fully-denoised image generated of the base model
can be further improved using the [refiner checkpoint](huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9).
can be further improved using the [refiner checkpoint](huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0).
For this, you simply run the refiner as a normal image-to-image pipeline after the "base" text-to-image
pipeline. You can leave the outputs of the base model in latent space.
@@ -229,12 +229,12 @@ from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
refiner = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-refiner-0.9",
"stabilityai/stable-diffusion-xl-refiner-1.0",
text_encoder_2=pipe.text_encoder_2,
vae=pipe.vae,
torch_dtype=torch.float16,
@@ -267,12 +267,12 @@ from diffusers import StableDiffusionXLInpaintPipeline
from diffusers.utils import load_image
pipe = StableDiffusionXLInpaintPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
refiner = StableDiffusionXLInpaintPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-refiner-0.9",
"stabilityai/stable-diffusion-xl-refiner-1.0",
text_encoder_2=pipe.text_encoder_2,
vae=pipe.vae,
torch_dtype=torch.float16,
@@ -321,12 +321,12 @@ from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipelin
import torch
pipe = StableDiffusionXLPipeline.from_single_file(
"./sd_xl_base_0.9.safetensors", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"./sd_xl_base_1.0.safetensors", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")
refiner = StableDiffusionXLImg2ImgPipeline.from_single_file(
"./sd_xl_refiner_0.9.safetensors", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
"./sd_xl_refiner_1.0.safetensors", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
)
refiner.to("cuda")
```
@@ -399,7 +399,7 @@ from diffusers import StableDiffusionXLPipeline
import torch
pipe = StableDiffusionXLPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipe.to("cuda")

4
examples/controlnet/README_sdxl.md
View File

@@ -61,7 +61,7 @@ wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/ma
Then run `huggingface-cli login` to log into your Hugging Face account. This is needed to be able to push the trained ControlNet parameters to Hugging Face Hub.
```bash
export MODEL_DIR="stabilityai/stable-diffusion-xl-base-0.9"
export MODEL_DIR="stabilityai/stable-diffusion-xl-base-1.0"
export OUTPUT_DIR="path to save model"
accelerate launch train_controlnet_sdxl.py \
@@ -98,7 +98,7 @@ from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel, UniP
from diffusers.utils import load_image
import torch
base_model_path = "stabilityai/stable-diffusion-xl-base-0.9"
base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
controlnet_path = "path to controlnet"
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)

2
examples/controlnet/train_controlnet_sdxl.py
View File

@@ -231,7 +231,7 @@ These are controlnet weights trained on {base_model} with new type of conditioni
## License
[SDXL 0.9 Research License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/blob/main/LICENSE.md)
[SDXL 1.0 License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)
"""
with open(os.path.join(repo_folder, "README.md"), "w") as f:
f.write(yaml + model_card)

6
examples/dreambooth/README_sdxl.md
View File

@@ -76,7 +76,7 @@ This will also allow us to push the trained LoRA parameters to the Hugging Face
Now, we can launch training using:
```bash
export MODEL_NAME="stabilityai/stable-diffusion-xl-base-0.9"
export MODEL_NAME="stabilityai/stable-diffusion-xl-base-1.0"
export INSTANCE_DIR="dog"
export OUTPUT_DIR="lora-trained-xl"
@@ -127,7 +127,7 @@ image = pipe("A picture of a sks dog in a bucket", num_inference_steps=25).image
image.save("sks_dog.png")
```
We can further refine the outputs with the [Refiner](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9):
We can further refine the outputs with the [Refiner](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0):
```python
from huggingface_hub.repocard import RepoCard
@@ -145,7 +145,7 @@ pipe.load_lora_weights(lora_model_id)
# Load the refiner.
refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-refiner-0.9", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
"stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
)
refiner.to("cuda")

2
examples/dreambooth/train_dreambooth_lora_sdxl.py
View File

@@ -97,7 +97,7 @@ Special VAE used for training: {vae_path}.
## License
[SDXL 0.9 Research License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/blob/main/LICENSE.md)
[SDXL 1.0 License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)
"""
with open(os.path.join(repo_folder, "README.md"), "w") as f:
f.write(yaml + model_card)

8
examples/instruct_pix2pix/README_sdxl.md
View File

@@ -15,7 +15,7 @@ training procedure while being faithful to the [original implementation](https:/
Refer to the original InstructPix2Pix training example for installing the dependencies.
You will also need to get access of SDXL by filling the [form](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9).
You will also need to get access of SDXL by filling the [form](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
### Toy example
@@ -26,7 +26,7 @@ Configure environment variables such as the dataset identifier and the Stable Di
checkpoint:
```bash
export MODEL_NAME="stabilityai/stable-diffusion-xl-base-0.9"
export MODEL_NAME="stabilityai/stable-diffusion-xl-base-1.0"
export DATASET_ID="fusing/instructpix2pix-1000-samples"
```
@@ -51,7 +51,7 @@ with Weights and Biases. You can enable this feature with `report_to="wandb"`:
```bash
python train_instruct_pix2pix_xl.py \
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-0.9 \
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0 \
--dataset_name=$DATASET_ID \
--use_ema \
--enable_xformers_memory_efficient_attention \
@@ -80,7 +80,7 @@ for running distributed training with `accelerate`. Here is an example command:
```bash
accelerate launch --mixed_precision="fp16" --multi_gpu train_instruct_pix2pix.py \
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-0.9 \
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0 \
--dataset_name=$DATASET_ID \
--use_ema \
--enable_xformers_memory_efficient_attention \

2
src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
View File

@@ -50,7 +50,7 @@ EXAMPLE_DOC_STRING = """
>>> from diffusers import StableDiffusionXLPipeline
>>> pipe = StableDiffusionXLPipeline.from_pretrained(
... "stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16
... "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")

2
src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py
View File

@@ -52,7 +52,7 @@ EXAMPLE_DOC_STRING = """
>>> from diffusers.utils import load_image
>>> pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(
... "stabilityai/stable-diffusion-xl-refiner-0.9", torch_dtype=torch.float16
... "stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> url = "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png"

2
src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py
View File

@@ -47,7 +47,7 @@ EXAMPLE_DOC_STRING = """
>>> from diffusers.utils import load_image
>>> pipe = StableDiffusionXLInpaintPipeline.from_pretrained(
... "stabilityai/stable-diffusion-xl-base-0.9",
... "stabilityai/stable-diffusion-xl-base-1.0",
... torch_dtype=torch.float16,
... variant="fp16",
... use_safetensors=True,