[Docs] Pipelines for inference (#417)
* Update conditional_image_generation.mdx * Update unconditional_image_generation.mdx
This commit is contained in:
parent
a353c46ec0
commit
6b9906f6c2
|
@ -12,21 +12,39 @@ specific language governing permissions and limitations under the License.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# Quicktour
|
# Conditional Image Generation
|
||||||
|
|
||||||
Start using Diffusers🧨 quickly!
|
The [`DiffusionPipeline`] is the easiest way to use a pre-trained diffusion system for inference
|
||||||
To start, use the [`DiffusionPipeline`] for quick inference and sample generations!
|
|
||||||
|
|
||||||
|
Start by creating an instance of [`DiffusionPipeline`] and specify which pipeline checkpoint you would like to download.
|
||||||
|
You can use the [`DiffusionPipeline`] for any [Diffusers' checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads).
|
||||||
|
In this guide though, you'll use [`DiffusionPipeline`] for text-to-image generation with [Latent Diffusion](https://huggingface.co/CompVis/ldm-text2im-large-256):
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> from diffusers import DiffusionPipeline
|
||||||
|
|
||||||
|
>>> generator = DiffusionPipeline.from_pretrained("CompVis/ldm-text2im-large-256")
|
||||||
```
|
```
|
||||||
pip install diffusers
|
The [`DiffusionPipeline`] downloads and caches all modeling, tokenization, and scheduling components.
|
||||||
|
Because the model consists of roughly 1.4 billion parameters, we strongly recommend running it on GPU.
|
||||||
|
You can move the generator object to GPU, just like you would in PyTorch.
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> generator.to("cuda")
|
||||||
```
|
```
|
||||||
|
|
||||||
## Main classes
|
Now you can use the `generator` on your text prompt:
|
||||||
|
|
||||||
### Models
|
```python
|
||||||
|
>>> image = generator("An image of a squirrel in Picasso style").images[0]
|
||||||
|
```
|
||||||
|
|
||||||
### Schedulers
|
The output is by default wrapped into a [PIL Image object](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class).
|
||||||
|
|
||||||
### Pipeliens
|
You can save the image by simply calling:
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> image.save("image_of_squirrel_painting.png")
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -12,21 +12,41 @@ specific language governing permissions and limitations under the License.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# Quicktour
|
# Unonditional Image Generation
|
||||||
|
|
||||||
Start using Diffusers🧨 quickly!
|
The [`DiffusionPipeline`] is the easiest way to use a pre-trained diffusion system for inference
|
||||||
To start, use the [`DiffusionPipeline`] for quick inference and sample generations!
|
|
||||||
|
|
||||||
|
Start by creating an instance of [`DiffusionPipeline`] and specify which pipeline checkpoint you would like to download.
|
||||||
|
You can use the [`DiffusionPipeline`] for any [Diffusers' checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads).
|
||||||
|
In this guide though, you'll use [`DiffusionPipeline`] for unconditional image generation with [DDPM](https://arxiv.org/abs/2006.11239):
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> from diffusers import DiffusionPipeline
|
||||||
|
|
||||||
|
>>> generator = DiffusionPipeline.from_pretrained("google/ddpm-celebahq-256")
|
||||||
```
|
```
|
||||||
pip install diffusers
|
The [`DiffusionPipeline`] downloads and caches all modeling, tokenization, and scheduling components.
|
||||||
|
Because the model consists of roughly 1.4 billion parameters, we strongly recommend running it on GPU.
|
||||||
|
You can move the generator object to GPU, just like you would in PyTorch.
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> generator.to("cuda")
|
||||||
```
|
```
|
||||||
|
|
||||||
## Main classes
|
Now you can use the `generator` on your text prompt:
|
||||||
|
|
||||||
### Models
|
```python
|
||||||
|
>>> image = generator().images[0]
|
||||||
|
```
|
||||||
|
|
||||||
|
The output is by default wrapped into a [PIL Image object](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class).
|
||||||
|
|
||||||
|
You can save the image by simply calling:
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> image.save("generated_image.png")
|
||||||
|
```
|
||||||
|
|
||||||
### Schedulers
|
|
||||||
|
|
||||||
### Pipeliens
|
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue