Metadata-Version: 2.1
Name: perceptor
Version: 0.6.5
Summary: Modular image generation library
Home-page: https://github.com/samedii/perceptor
Author: Richard Löwenström
Author-email: samedii@gmail.com
Requires-Python: >=3.8,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Requires-Dist: Pillow (>=9.0.1,<10.0.0)
Requires-Dist: basicsr (>=1.4.2,<2.0.0)
Requires-Dist: diffusers (>=0.5.1,<0.6.0)
Requires-Dist: dill (>=0.3.4,<0.4.0)
Requires-Dist: einops (>=0.4.0,<0.5.0)
Requires-Dist: ftfy (>=6.0.3,<7.0.0)
Requires-Dist: imageio (>=2.14.1,<3.0.0)
Requires-Dist: kornia (>=0.6.3,<0.7.0)
Requires-Dist: lpips (>=0.1.4,<0.2.0)
Requires-Dist: more-itertools (>=8.12.0,<9.0.0)
Requires-Dist: ninja (>=1.10.2,<2.0.0)
Requires-Dist: numpy (>=1.22.2,<2.0.0)
Requires-Dist: omegaconf (>=2.1.1,<3.0.0)
Requires-Dist: open-clip-torch (>=2.0.2,<3.0.0)
Requires-Dist: opencv-python (>=4.5.4,<5.0.0,!=4.6.0.66)
Requires-Dist: pytorch-lantern (>=0.12.0,<0.13.0)
Requires-Dist: pytorch-zero-lit (>=0.2.2,<0.3.0)
Requires-Dist: resmem (>=1.1.4,<2.0.0)
Requires-Dist: taming-transformers-rom1504 (>=0.0.6,<0.0.7)
Requires-Dist: timm (>=0.5.4,<0.6.0)
Requires-Dist: torch (>=1.12.1,<2.0.0)
Requires-Dist: torchvision
Requires-Dist: tqdm (>=4.62.3,<5.0.0)
Requires-Dist: transformers (>=4.21.1,<5.0.0)
Requires-Dist: triton (>=1.1.1,<2.0.0)
Requires-Dist: xformers (>=0.0.13,<0.0.14)
Requires-Dist: youtokentome (>=1.0.6,<2.0.0)
Project-URL: Repository, https://github.com/samedii/perceptor
Description-Content-Type: text/markdown

# perceptor

Modular image generation library.

## Install

```bash
poetry add perceptor
```

Or, for the old timers:

```bash
pip install perceptor
```

### CUDA 11.3 (Support RTX cards)

```bash
poetry run pip uninstall torch torchvision -y && poetry run pip install torch==1.12.1 torchvision==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu113
```

_Stable Diffusion Flash Attention optimization with xformers_.

```bash
poetry run pip uninstall triton xformers -y && poetry run pip install triton xformers
```

## Interface

Shortlist of available features. See the [API reference](https://perceptor.readthedocs.io/en/latest/) for more information.

```python
perceptor
  .drawers
    .BruteDiffusion
    .DeepImagePrior
    .Raw
    .RuDALLE
    .StyleGANXL
  .models
    .AdaBinsDepth
    .DeepImagePrior
    .VelocityDiffusion (yfcc_2, yfcc_1, cc12m_1_cfg, wikiart)
    .latent_diffusion
      .Text2Image
      .Face
      .SuperResolution
    .GuidedDiffusion (openai, pixelart)
    .MidasDepth
    .MonsterDiffusion (all, tinyhero)
    .StyleGANXL
    .RuDALLE
    .StableDiffusion
    .SuperResolution
  .losses
    # Text-image similarity
    .BLIP
    .CLIP
    .CLOOB
    .LiT
    .GlideCLIP
    .OpenCLIP
    .OWLViT
    .RuCLIP
    .SLIP
    # Other
    .AestheticVisualAssessment
    .LPIPS
    .Memorability
    .MidasDepth
    .SimulacraAesthetic
    .Smoothness
    .StyleTransfer
  .transforms
    .clamp_with_grad
    .resize
    .SuperResolution
  .utils
    .gradient_checkpoint
```

