https://github.com/ai-forever/ru-dalle

Generate images from texts. In Russian

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
✓
Committers with academic emails
1 of 19 committers (5.3%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (7.6%) to scientific vocabulary

Keywords

dalle image-generation openai python pytorch russian russian-language text-to-image transformer

Keywords from Contributors

jax speech-recognition cryptography distillation vlm qwen pytorch-transformers pretrained-models model-hub glm

Last synced: 6 months ago · JSON representation

Repository

Generate images from texts. In Russian

Basic Info

Host: GitHub
Owner: ai-forever
License: apache-2.0
Language: Jupyter Notebook
Default Branch: master
Homepage: https://rudalle.ru/
Size: 26.9 MB

Statistics

Stars: 1,646
Watchers: 37
Forks: 245
Open Issues: 37
Releases: 0

Topics

dalle image-generation openai python pytorch russian russian-language text-to-image transformer

Created over 4 years ago · Last pushed about 3 years ago

Metadata Files

Readme License

ruDALL-E

Generate images from texts

pip install rudalle==1.1.3

🤗 HF Models:

ruDALL-E Malevich (XL) \ ruDALL-E Emojich (XL) (readme here) \ ruDALL-E Surrealist (XL) \ ruDALL-E Kandinsky (XXL) (soon)

Minimal Example:

Example usage ruDALL-E Malevich (XL) with 3.5GB vRAM!

Finetuning example

generation by ruDALLE:

```python import ruclip from rudalle.pipelines import generateimages, show, superresolution, cherrypickbyruclip from rudalle import getrudallemodel, gettokenizer, getvae, getrealesrgan from rudalle.utils import seed_everything

prepare models:

device = 'cuda' dalle = getrudallemodel('Malevich', pretrained=True, fp16=True, device=device) tokenizer = gettokenizer() vae = getvae(dwt=True).to(device)

pipeline utils:

realesrgan = getrealesrgan('x2', device=device) clip, processor = ruclip.load('ruclip-vit-base-patch32-384', device=device) clippredictor = ruclip.Predictor(clip, processor, device, bs=8) text = 'радуга на фоне ночного города'

seedeverything(42) pilimages = [] scores = [] for topk, topp, imagesnum in [ (2048, 0.995, 24), ]: _pilimages, scores = generateimages(text, tokenizer, dalle, vae, topk=topk, imagesnum=imagesnum, bs=8, topp=topp) pilimages += _pilimages scores += _scores

show(pil_images, 6) ```

auto cherry-pick by ruCLIP:

python top_images, clip_scores = cherry_pick_by_ruclip(pil_images, text, clip_predictor, count=6) show(top_images, 3)

super resolution:

python sr_images = super_resolution(top_images, realesrgan) show(sr_images, 3)

python text, seed = 'красивая тян из аниме', 6955

Image Prompt

see jupyters/ruDALLE-image-prompts-A100.ipynb python text, seed = 'Храм Василия Блаженного', 42 skyes = [red_sky, sunny_sky, cloudy_sky, night_sky]

VideoDALL-E | ruCogVideo by @cene555

Video generation example Finetuning example

Aspect ratio images -->NEW<--

Kandinsky 12B

Request access: Here

роботы акварелью в стиле ван гога

FID = 15.4 (COCO Valid)

🚀 Contributors 🚀

@bes shared great idea and realization with IDWT for decoding images with higher quality 512x512! 😈💪 thanks a lot for your constructive advices, appreciate it
@neverix thanks a lot for contributing for speed up of inference
@Igor Pavlov trained model and prepared code with super-resolution
@oriBetelgeuse thanks a lot for easy API of generation using image prompt
@Alex Wortega created first FREE version colab notebook with fine-tuning ruDALL-E Malevich (XL) on sneakers domain 💪
@Anton Lozhkov Integrated to Huggingface Spaces with Gradio, see here

Supported by

Social Media

Owner

Name: AI Forever
Login: ai-forever
Kind: organization
Location: Armenia

Repositories: 60
Profile: https://github.com/ai-forever

Creating ML for the future. AI projects you already know. We are non-profit organization with members from all over the world.

GitHub Events

Total

Watch event: 14
Fork event: 5

Last Year

Watch event: 14
Fork event: 5

Committers

Last synced: 9 months ago

All Time

Total Commits: 117
Total Committers: 19
Avg Commits per committer: 6.158
Development Distribution Score (DDS): 0.521

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
shonenkov	s**v@p**u	56
Alex Shonenkov	s**v@A**l	17
blue-fish	6****h	6
neverix	s**p@g**m	6
pre-commit-ci[bot]	6****]	5
Shahmatov Arseniy	6****5	4
Arkhipkin Vladimir	3****e	3
Tatiana Shavrina	r**s@g**m	3
boomb0om	i**1@g**m	3
Aaron Gokaslan	s**n@g**m	2
AndrewTrefilov	I**I@m**u	2
Denis	d**v@g**m	2
Oleh Shliazhko	o****r	2
AK391	8****1	1
Alex Wortega	a**h@g**m	1
Anastasia Maltseva	n**a@m**u	1
Denis	k**n@b**u	1
Ksenia Ivanova	9****u	1
Max Woolf	m**x@m**m	1

Committer Domains (Top 20 + Academic)

mail.ru: 2 minimaxir.com: 1 bk.ru: 1 phystech.edu: 1

Issues and Pull Requests

Last synced: 9 months ago

All Time

Total issues: 77
Total pull requests: 60
Average time to close issues: 4 months
Average time to close pull requests: 10 days
Total issue authors: 57
Total pull request authors: 21
Average comments per issue: 1.83
Average comments per pull request: 0.33
Merged pull requests: 51
Bot issues: 0
Bot pull requests: 3

Past Year

Issues: 1
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 1
Pull request authors: 0
Average comments per issue: 0.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

eyaler (5)
bibyts (5)
bitcoin5000 (4)
loretoparisi (3)
Sidiusz (3)
mkaskov (2)
XieBaoshi (2)
johnpaulbin (2)
neverix (2)
DIMONZAKIEV (1)
Cr0c81 (1)
j-min (1)
anshul-garg-drishya (1)
purrden (1)
Baekpica (1)

Pull Request Authors

shonenkov (20)
neverix (7)
AlexWortega (4)
ghost (3)
oriBetelgeuse (3)
pre-commit-ci[bot] (3)
boomb0om (2)
Skylion007 (2)
ollmer (2)
denndimitrov (2)
cene555 (2)
saurabhbikram (1)
demirklvc (1)
minimaxir (1)
AndrewTrefilov (1)

Top Labels

Issue Labels

Pull Request Labels

Packages

Total packages: 1
Total downloads: unknown

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 2

proxy.golang.org: github.com/ai-forever/ru-dalle

Documentation: https://pkg.go.dev/github.com/ai-forever/ru-dalle#section-documentation
License: apache-2.0
Latest release: v1.1.0
published over 3 years ago

Versions: 2
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 7.0%

Last synced: 6 months ago

Dependencies

requirements-test.txt pypi

pre-commit * test
pytest * test
pytest-cov * test

requirements.txt pypi

PyWavelets ==1.1.1
einops *
matplotlib *
more_itertools *
omegaconf >=2.0.0
opencv-python ==4.5.4.60
segmentation-models-pytorch ==0.1.3
taming-transformers ==0.0.1
torch *
torchvision *
transformers *
youtokentome *

https://github.com/ai-forever/ru-dalle

Science Score: 10.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

ruDALL-E

Generate images from texts

🤗 HF Models:

Minimal Example:

generation by ruDALLE:

prepare models:

pipeline utils:

auto cherry-pick by ruCLIP:

super resolution:

Image Prompt

VideoDALL-E | ruCogVideo by @cene555

Aspect ratio images -->NEW<--

Kandinsky 12B

🚀 Contributors 🚀

Supported by

Social Media

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

proxy.golang.org: github.com/ai-forever/ru-dalle

Rankings

Dependencies