Spilio

[Spilio @spiliodev]

@david_attisaas chaud pour nantes

[Spilio @spiliodev]

@levelsio thx for telling the truth homie, much needed 👊

[Spilio @spiliodev]

@LuteWallet will we be able to register before Algorand 4.0 is fully rolled out for the 2A keyreg fee? Or do we have to wait until next week? thx

[Spilio @spiliodev]

@alexgrbu algorithm

[Spilio @spiliodev]

@thibaudz Are you familiar with APIs ? You could just use https://t.co/oynALRmeHM for that. Call the whisper model and parse the JSON response. You can use VTT or SRT for transcription parameter and that will give you the actual caption file.

Link to the model: https://t.co/xblfCXApNy

[Spilio @spiliodev]

@thibaudz Dude that's awesome !

[Spilio @spiliodev]

@thibaudz @pika_labs @coqui_ai Great work man ! C'est très propre !

[Spilio @spiliodev]

@EMostaque Sounds perfectly fair

[Spilio @spiliodev]

@levelsio @runwayml @ElevenLabs Thanks !

[Spilio @spiliodev]

@Ninjascalp 4

[Spilio @spiliodev]

@Ninjascalp lets gooo

[Spilio @spiliodev]

@Ninjascalp lets gooo

[Spilio @spiliodev]

@Ninjascalp WE. TOLDED. YOU.

[Spilio @spiliodev]

@Toby_Frank @EMostaque no fine tuning?

[Spilio @spiliodev]

@Ninjascalp but they won't trap me

[Spilio @spiliodev]

@Ninjascalp but they won't trap me

[Spilio @spiliodev]

@levelsio That can also be fine tuned with a character/word aware model. For example, instead of using dreambooth try to fine tune your current model with images using the following caption "..., wearing a tshirt with the message anti social social club" https://t.co/JE4fTyjSJX

[Spilio @spiliodev]

@levelsio Nice! Using Waifu diffusion training code + BLIP captioned pics from Unsplash I suppose? Or simply textual inversion? Looking forward to see the final result, keep up the great work!

[Spilio @spiliodev]

@thibaudz @cloneofsimo gotcha, thx for sharing your results

[Spilio @spiliodev]

@thibaudz @cloneofsimo Pretty interesting results, face still looking a bit blurry but that could be fixed with GFPGAN.
How many pictures + steps per picture? Also whats you hit rate with best working prompt?