@[email protected]

Mastodon : @[email protected]
developer - musician - visual artist

[@[email protected] @SioudaYassin]

Hémicycle disponible sur le Simulateur d'assemblée grace à la contribution de Jean-Michel Pothelune

C'est par ici :) => https://t.co/gNhxwVZM5k

[@[email protected] @SioudaYassin]

Stack:
- @sveltejs
- @langchain
- @AIatMeta llama3.1:8b
- une carte graphique (si c'est lent c'est parce qu'il y en a qu'une )

Merci Jean-Michel P qui m'a glissé l'idée !

[@[email protected] @SioudaYassin]

Projet inutile du jour : Simulateur d'Assemblée Nationale

Simulateur interactif qui permettra de tester ses compétences législatives en rédigeant et en soumettant un texte de loi à l'examen des députes virtuels.

https://t.co/gNhxwVZM5k

[@[email protected] @SioudaYassin]

Bye ;)
@[email protected]

https://t.co/2HgfcfSIi0

[Captain Disillusion @CDisillusion]

I’ve decided to follow suit and will no longer feast upon the souls of all humans who happen to see my videos.

[RJ Palmer @arvalis]

DeviantArt has decided your artwork there is fair game to be used in their new AI generator by default. You have to go to an obscure form to opt-out and requires 10 days to be reviewed.

[Omer Bar Tal @omerbartal]

Played with optimizing Neural Atlases through Stable Diffusion. So much fun! Here are a few examples of video edits:

@RafailFridman @DanahYatim

[mayatérialiste 🏳️‍⚧️ @mayaterialiste]

Quand j'étais enfant j'ai toujours trouvé assez mystérieux et frustrant cette manière de crypter l'image sur Canal+. En fait il y a pas mal de choses intéressantes à dire sur cette chaine et les technologies employées : 🧻🧶

[Shubhro Saha @shubroski]

This weekend I built =GPT3(), a way to run GPT-3 prompts in Google Sheets.

It's incredible how tasks that are hard or impossible to do w/ regular formulas become trivial.

For example: sanitize data, write thank you cards, summarize product reviews, categorize feedback...

[@[email protected] @SioudaYassin]

@Norod78 Probably missing some reference points with this black background

[ALDIL (Lyon) @aldil_lyon]

Appel à participation aux JdLL 2023
L'appel à participation des JdLL 2023 est ouvert, n'hésitez pas à proposer des interventions : https://t.co/Px9YRuJu7d. Pour plus d'informations sur l'évènement, c'est par ici : https://t.co/aVGLmjH1TQ.

Logo des JdLL… https://t.co/WnM39Et1yl

[Radamés Ajna @radamar]

Here is the link for the #StableDiffusion multiplayer experiment.

https://t.co/PBOwaTjMEo

If the frame is empty, we run text2img. Otherwise, we inpaint/outpaint empty areas. You can zoom, draw a custom mask or override painted areas. Looking forward to seeing what you create.

[AK @_akhaliq]

Cyberpunk-Anime-Diffusion: finetuned Waifu Diffusion V1.3 Model with Stable Diffusion V1.5 New Vae, training in Dreambooth by @DGSpitzer

@huggingface model: https://t.co/7BdWIBTmM8

[Nitrosocke @Nitrosocke]

New Model out now! Check it out on @huggingface
Link in the description ⤵️

[AK @_akhaliq]

The @Gradio Demo for Cyberpunk Anime Diffusion: finetuned Waifu Diffusion V1.3 Model with Stable Diffusion V1.5 New Vae, training in Dreambooth is out on @huggingface Spaces by @DGSpitzer

demo: https://t.co/w7Lf5yZnI5

[Axel Chemla--Romeu-Santos @axel_crs]

Very excited to organize the second ACIDS Workshop Beta this 5/11! This event aims to promote research&music interfaces in music AI through an experimental approach of these techniques. Looking forward to perform with @antoine_caillon, @hugoscurto, @MaximeMantovan1 and others!

[Peter Yang @petergyang]

Why AI will never replace human creativity no matter how good it gets:

[Omar Sanseviero @osanseviero]

Yesterday @GoogleAI released Flan T5, a model that can solve 1800 different tasks 🤯

Since then
- Open-source models: https://t.co/X6q4mLouR0
- Support in @huggingface transformers
- An interactive demo I created to play with the model https://t.co/49e6MkN14E

[Lnyan @lkwq007]

A major update of stablediffusion-infinity has been released with a redesigned UI and better generation quality!
The @runwayml Stable Diffusion inpainting model significantly improves the #outpainting quality.

Source Code: https://t.co/BpUWQZuCqF
Demo: https://t.co/6s8sbsc6Qz

[Marco Pasini @marco_ppasini]

🎵 Musika generates 44.1 kHz stereo music in an instant 🎵

You can now train Musika on your own music dataset (from scratch or by finetuning) with a single consumer GPU!

Demo (New!): https://t.co/z5zWmSbtxD
Code: https://t.co/i6ogu0QZfA

Techno, Metal, Lofi in the video below: