No lights, no cameras, all action Gen-1 lets you turn existing videos into new, compelling pieces of footage with just images or text prompts.
MULTIMODAL AI
-
Open Source Speech Synthesis Models: FastSpeech2, VITS, TorToise
By
–
Yes! My point was referring specific to closed source API the David was mentioning in the video.
All, FastSpeech2, VITS and TorToise (inference) are OSS. :)) -
Simpsons Intro in Experimental Cubist Stop Motion with Runway AI
By
–
La intro de los Simpson pero en estilo stop motion cubista experimental creada con la IA de Runway Gen 1! https://t.co/5XGf0eM6Vx
— Carlos Santana (@DotCSV) 10 février 2023La intro de los Simpson pero en estilo stop motion cubista experimental creada con la IA de Runway Gen 1!
-
SpeechT5 vs FastSpeech2 vs VITS: TTS Model Comparison
By
–
Ofcourse. It depends on what do you optimise for SpeechT5 TTS (AR) does sound better than vanilla FastSpeech2 (NAR) however worse than VITS/PortaSpeech. Significantly worse than TorToise TTS. However it is considerably slow.
-
Hugging Face Diffusers: Pre-trained Diffusion Models for Vision and Audio
By
–
4. Hugging Face Diffusers We are noticing the recent trend with applications using Diffusion Models either it can be Stable Diffusion or Dalle E Diffusers library provide you with pre trained diffusion models across vision and audio. Check this: https://
github.com/huggingface/di
ffusers
… -
Transformers from Hugging Face: Pretrained Models for Text, Vision, Audio
By
–
1. Transformers from Hugging Face Transformers library provides you with thousands of pretrained models to perform tasks on text, vision, and audio. This will help you with leveraging the already existing models instead of building them from scratch. https://
github.com/huggingface/tr
ansformers
… -
Open Source AI Models: Flan, OPT-IML, Speech T5 Alternative
By
–
Somebody tell my boi about @huggingface! You can replicate the same more or less (if not better) with Flan/ OPT-IML and Speech T5 TTS on the 🤗hub: https://t.co/fyV1nkC7I0
— Vaibhav (VB) Srivastav (@reach_vb) 10 février 2023
That’s the power of open source ⚡️ https://t.co/0trXRuup01Somebody tell my boi about @huggingface
! You can replicate the same more or less (if not better) with Flan/ OPT-IML and Speech T5 TTS on the hub: https://
huggingface.co/blog/speecht5 That’s the power of open source -
Nice Tests Facial Recognition at Rugby World Cup
By
–
Nice wants to test a facial recognition system during the rugby world cup https://actuia.com/actualite/nice-veut-tester-un-dispositif-de-reconnaissance-faciale-lors-de-la-coupe-du-monde-de-rugby/
… #AI #artificialintelligence -
PEZ integrated into KREA with optimized ViT-B/32 performance
By
–
we just added PEZ to KREA!
— KREA AI (@krea_ai) 10 février 2023
by using ViT-B/32 + a few changes in the original code it runs in less than 3s ⚡️https://t.co/zvSfXDRxJVwe just added PEZ to KREA! by using ViT-B/32 + a few changes in the original code it runs in less than 3s
-
KREA Canvas: AI-Powered Futuristic Coat Design Tool
By
–
"an image is worth a thousand prompts"
— KREA AI (@krea_ai) 10 février 2023
designing futuristic coats with image references in the KREA Canvas ⚡️
we keep sending invites as we can handle more users, sign up here https://t.co/M34dD3yXaw pic.twitter.com/inYGIqjuIB"an image is worth a thousand prompts" designing futuristic coats with image references in the KREA Canvas we keep sending invites as we can handle more users, sign up here https://
forms.gle/L8G6V1pzLx76Pu
R3A
…