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

[WIP][Docs] Use DiffusionPipeline Instead of Child Classes when Loading Pipeline (#2809)

Browse Source 
* Change the docs to use the parent DiffusionPipeline class when loading a checkpoint using from_pretrained() instead of a child class (e.g. StableDiffusionPipeline) where possible.

* Run make style to fix style issues.

* Change more docs to use DiffusionPipeline rather than a subclass.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
This commit is contained in:
dg845
2023-03-28 08:44:34 -07:00
committed by GitHub
parent 920a15cf70
commit 663c654577
7 changed files with 25 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docs/source/en/optimization/fp16.mdx
View File

@@ -45,7 +45,10 @@ torch.backends.cuda.matmul.allow_tf32 = True
To save more GPU memory and get more speed, you can load and run the model weights directly in half precision. This involves loading the float16 version of the weights, which was saved to a branch named `fp16`, and telling PyTorch to use the `float16` type when loading them:
```Python
pipe = StableDiffusionPipeline.from_pretrained(
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
torch_dtype=torch.float16,
@@ -72,13 +75,13 @@ For even additional memory savings, you can use a sliced version of attention th
each head which can save a significant amount of memory.
</Tip>
To perform the attention computation sequentially over each head, you only need to invoke [`~StableDiffusionPipeline.enable_attention_slicing`] in your pipeline before inference, like here:
To perform the attention computation sequentially over each head, you only need to invoke [`~DiffusionPipeline.enable_attention_slicing`] in your pipeline before inference, like here:
```Python
import torch
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained(
pipe = DiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
torch_dtype=torch.float16,
@@ -402,10 +405,10 @@ To leverage it just make sure you have:
- Cuda available
- [Installed the xformers library](xformers).
```python
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained(
pipe = DiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
torch_dtype=torch.float16,
).to("cuda")

4
docs/source/en/optimization/mps.mdx
View File

@@ -35,9 +35,9 @@ The snippet below demonstrates how to use the `mps` backend using the familiar `
We strongly recommend you use PyTorch 2 or better, as it solves a number of problems like the one described in the previous tip.
```python
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
pipe = pipe.to("mps")
# Recommended if your computer has < 64 GB of RAM

14
docs/source/en/optimization/torch2.0.mdx
View File

@@ -35,9 +35,9 @@ pip install --upgrade torch torchvision diffusers
```Python
import torch
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
@@ -48,10 +48,10 @@ pip install --upgrade torch torchvision diffusers
```Python
import torch
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
from diffusers.models.attention_processor import AttnProcessor2_0
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
pipe.unet.set_attn_processor(AttnProcessor2_0())
prompt = "a photo of an astronaut riding a horse on mars"
@@ -68,11 +68,9 @@ pip install --upgrade torch torchvision diffusers
```python
import torch
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to(
"cuda"
)
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
pipe.unet = torch.compile(pipe.unet)
batch_size = 10

2
docs/source/en/quicktour.mdx
View File

@@ -141,7 +141,7 @@ Different schedulers come with different denoising speeds and quality trade-offs
```py
>>> from diffusers import EulerDiscreteScheduler
>>> pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
>>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
>>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
```

6
docs/source/en/stable_diffusion.mdx
View File

@@ -47,9 +47,9 @@ Let's load the pipeline.
## Speed Optimization
``` python
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained(model_id)
pipe = DiffusionPipeline.from_pretrained(model_id)
```
We aim at generating a beautiful photograph of an *old warrior chief* and will later try to find the best prompt to generate such a photograph. For now, let's keep the prompt simple:
@@ -88,7 +88,7 @@ The default run we did above used full float32 precision and ran the default num
``` python
import torch
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
```

4
docs/source/en/training/dreambooth.mdx
View File

@@ -457,11 +457,11 @@ If you have **`"accelerate>=0.16.0"`** installed, you can use the following code
inference from an intermediate checkpoint:
```python
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
import torch
model_id = "path_to_saved_model"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
prompt = "A photo of sks dog in a bucket"
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]

4
docs/source/en/using-diffusers/using_safetensors.mdx
View File

@@ -75,9 +75,9 @@ And we're equipped with dealing with it.
Then in order to use the model, even before the branch gets accepted by the original author you can do:
```python
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", revision="refs/pr/22")
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", revision="refs/pr/22")
```
or you can test it directly online with this [space](https://huggingface.co/spaces/diffusers/check_pr).