This week's AI newsletter just dropped! This week’s features:
-BuzzFeed's 12% workforce cut
-AI powered eye contact
-Death to stock photography?
-1 glitch to make money with ChatGPT Read it in full here:
GENERATIVE AI
-
Weekly AI Newsletter: BuzzFeed Cuts, Eye Contact Tech, Stock Photos
By
–
-
Train Your Own MusicLM with MusicCaps Dataset
By
–
Want to train your own MusicLM? 🎶
— Vaibhav (VB) Srivastav (@reach_vb) 27 janvier 2023
The MusicCaps dataset is now on the 🤗Hub: https://t.co/JKrVYng9OY
The MusicCaps dataset contains 5,521 music examples, each of which is labeled with an English aspect list and a free text caption written by musicians. 🎸 pic.twitter.com/Byiy9r7hzsWant to train your own MusicLM? The MusicCaps dataset is now on the Hub: https://
huggingface.co/datasets/googl
e/MusicCaps
… The MusicCaps dataset contains 5,521 music examples, each of which is labeled with an English aspect list and a free text caption written by musicians. -
LangChain Hub Repository for AI Agents Development
By
–
currently just using the github repo for that https://
github.com/hwchase17/lang
chain-hub/tree/master/agents
… -
Loading Chains with LangChain Framework
By
–
To load chains: “`
from langchain.chains import load_chain chain = load_chain('lc://chains/path/to/file.json')
“` Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/chains/generic/from_hub.html
… -
Google LolNerf: Learn from One Look at Images
By
–
Learn more about it here – https://
ai.googleblog.com/2022/09/lolner
f-learn-from-one-look.html
… -
LOLNeRF: Combining GLO and NeRF for Novel View Synthesis
By
–
How does it work? The combination of Generative Latent Optimization (GLO) and neural radiance fields (NeRF) used in LOLNeRF is what sets it apart from other approaches. It achieves SOTA results for novel view synthesis and competitive results for depth estimation.
-
Music Generation AI Claims Overstated Says Critic
By
–
It's neat how this combines advances in language understanding with music mixing neural networks but "solved music generation"?? That's like arguing that a drum machine has "solved the rhythm problem"
-
AI Music Generation Without Vocals for Video Content
By
–
En mi caso para mis vídeos siempre busco música sin voz (incluso en Epidemic Sound) así que no sería uno de mis casos de uso. AAAAAUNQUE siempre molará ver algo así 🙂
-
AI Music Generation Service for YouTube Video Production
By
–
El servicio de música para los vídeos de YT que ahora mismo pago a través de un Epidemic Sound, pero con mayor flexibilidad de poder ajustar el estilo a lo que busco, duración, etc. En definitiva reducir tiempos de búsqueda de la canción perfecta, generándola directamente.
-
Google Project Conditions AI Models on Melodies and Text
By
–
Súper interesante el poder condicionar no sólo a texto, sino también a MELODÍAS.
— Carlos Santana (@DotCSV) 27 janvier 2023
Pe-pero Carlos… ¿y se puede utilizar?
A ver, no habéis visto que he dicho que el proyecto era de Google… 😅 pic.twitter.com/p7p0xyADBTSúper interesante el poder condicionar no sólo a texto, sino también a MELODÍAS. Pe-pero Carlos… ¿y se puede utilizar? A ver, no habéis visto que he dicho que el proyecto era de Google…