1
0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
2022-06-02 00:46:49 +02:00
2022-06-02 00:46:45 +02:00
2022-05-31 10:17:19 +02:00
2022-05-31 10:17:19 +02:00
2022-05-30 18:21:15 +02:00
2022-05-31 10:17:19 +02:00
2022-05-30 18:21:15 +02:00
2022-06-02 00:42:43 +02:00
2022-05-30 18:21:15 +02:00
2022-05-31 10:17:19 +02:00

Diffusers

Library structure:

├── models
│   ├── dalle2
│   │   ├── modeling_dalle2.py
│   │   ├── README.md
│   │   └── run_dalle2.py
│   ├── ddpm
│   │   ├── modeling_ddpm.py
│   │   ├── README.md
│   │   └── run_ddpm.py
│   ├── glide
│   │   ├── modeling_glide.py
│   │   ├── README.md
│   │   └── run_dalle2.py
│   ├── imagen
│   │   ├── modeling_dalle2.py
│   │   ├── README.md
│   │   └── run_dalle2.py
│   └── latent_diffusion
│       ├── modeling_latent_diffusion.py
│       ├── README.md
│       └── run_latent_diffusion.py
├── src
│   └── diffusers
│       ├── configuration_utils.py
│       ├── __init__.py
│       ├── modeling_utils.py
│       ├── models
│       │   └── unet.py
│       ├── processors
│       └── samplers
│           ├── gaussian.py
├── tests
│   └── test_modeling_utils.py

Dummy Example

from diffusers import UNetModel, GaussianDiffusion
import torch

# 1. Load model
unet = UNetModel.from_pretrained("fusing/ddpm_dummy")

# 2. Do one denoising step with model
batch_size, num_channels, height, width = 1, 3, 32, 32
dummy_noise = torch.ones((batch_size, num_channels, height, width))
time_step = torch.tensor([10])
image = unet(dummy_noise, time_step)

# 3. Load sampler
sampler = GaussianDiffusion.from_config("fusing/ddpm_dummy")

# 4. Sample image from sampler passing the model
image = sampler.sample(model, batch_size=1)

print(image)
Description
🤗 Diffusers: современные диффузионные модели для генерации изображений, видео и аудио в PyTorch.
Readme Apache-2.0 754 MiB
Languages
Python 100%