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 NOTICE: This package is obsolete !!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
Release files for nataili 0.3.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| nataili-0.3.4.tar.gz | 884.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nataili-0.3.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.1 MB
Release files / nataili-0.3.4.tar.gz
| Download URL | nataili-0.3.4.tar.gz |
|---|---|
| Size | 884.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
51d64e45a4ce86e48a4cad0aca21278907e88c6ad8b0d6729c4bc931de6991f3
|
|
BLAKE2b-256 checksum How to use checksums |
32ab2c5fb86f913ea1939a26be61ba75b1e479eb3b97f12c66ddc6f39aa99dec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.11.3
|
Release files / nataili-0.3.4-py3-none-any.whl
| Download URL | nataili-0.3.4-py3-none-any.whl |
|---|---|
| Size | 1.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ad492e5b19b0ab9b262285436c27a1030ad2ab1275caf743ebbbc496a006283f
|
|
BLAKE2b-256 checksum How to use checksums |
4019f82639a3fc39dc0a6512596ba216a4622b4b5517b2f3d14b09281f579dd0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.11.3
|