Nataili: Multimodal AI Python Library
Project description
Nataili: Multimodal AI Python Library
!! NOTICE: This package is obsolete !!
Please switch to using hordelib which is based on ComfyUI.
Nataili is a Python library that provides tools for building multimodal AI applications. With its modular design, Nataili makes it easy to use only the tools you need to build custom AI solutions.
Some of the technologies included in Nataili are:
- AITemplate: Fast diffusion
- BLIP: Image captioning
- CLIP: Interrogation (ranking, similarity), Embedding (text, image) with cache support
- CLIP+MLP Predictor
- CodeFormer: Post-processing and super-resolution for faces
- ESRGAN: Image super-resolution
- GFPGAN: Post-processing for faces
- LAION-CoCa: Image captioning
- Stable Diffusion: Image generation
- SD Upscaler: latent diffusion upscaler for Stable Diffusion's autoencoder
- Train: Training tools for Stable Diffusion and CLIP+MLP Predictor
Projects using Nataili
Installation
pip install nataili
From source:
git clone https://github.com/db0/nataili
cd nataili
pip install -e .
Documentation
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nataili-0.3.4.tar.gz
(884.3 kB
view details)
Built Distribution
File details
Details for the file nataili-0.3.4.tar.gz
.
File metadata
- Download URL: nataili-0.3.4.tar.gz
- Upload date:
- Size: 884.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 51d64e45a4ce86e48a4cad0aca21278907e88c6ad8b0d6729c4bc931de6991f3 |
|
MD5 | 65d153a8370da9cb1de0fc2debd2f155 |
|
BLAKE2b-256 | 32ab2c5fb86f913ea1939a26be61ba75b1e479eb3b97f12c66ddc6f39aa99dec |
File details
Details for the file nataili-0.3.4-py3-none-any.whl
.
File metadata
- Download URL: nataili-0.3.4-py3-none-any.whl
- Upload date:
- Size: 1.2 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ad492e5b19b0ab9b262285436c27a1030ad2ab1275caf743ebbbc496a006283f |
|
MD5 | 9acf14efa7b261555f00319d1c948157 |
|
BLAKE2b-256 | 4019f82639a3fc39dc0a6512596ba216a4622b4b5517b2f3d14b09281f579dd0 |