Sales pfp

Sales

@isx

159 Following
67 Followers
Gabriellaa pfp
Gabriellaa
@skq
0 reply
9 recasts
35 reactions
Henríquez pfp
Henríquez
@hws
0 reply
4 recasts
19 reactions
Sales pfp
Sales
@isx
0 reply
1 recast
7 reactions
Sales pfp
Sales
@isx
O tempo vai esfriar, está difícil chegar o verão esse ano
2 replies
2 recasts
6 reactions
Jaguar pfp
Jaguar
@jwo
4 replies
8 recasts
22 reactions
Gabriel pfp
Gabriel
@ksx
2 replies
4 recasts
10 reactions
Sales pfp
Sales
@isx
Gostei dessa
0 reply
0 recast
0 reaction
Jéssica Ramos pfp
Jéssica Ramos
@jxl
Não de um peixe para uma pessoa, ensinei ela pescar
3 replies
1 recast
5 reactions
Henríquez pfp
Henríquez
@hws
0 reply
4 recasts
20 reactions
Sales pfp
Sales
@isx
Hoje nadei 1250 MTS, foi meu Record desde que entrei na natação
4 replies
3 recasts
21 reactions
Sales pfp
Sales
@isx
Esses dias vi um tucano, nem os bichos querem ficar na floresta kkk
0 reply
0 recast
0 reaction
Jéssica Ramos pfp
Jéssica Ramos
@jxl
Tem uma coruja no telhado da minha casa, esses bichos estão cada vez mais urbanos
5 replies
1 recast
23 reactions
Gatoline pfp
Gatoline
@ilq
0 reply
13 recasts
29 reactions
Yara pfp
Yara
@dso
0 reply
6 recasts
29 reactions
Jordan pfp
Jordan
@cka
1 reply
5 recasts
32 reactions
Jéssica Ramos pfp
Jéssica Ramos
@jxl
0 reply
3 recasts
31 reactions
Jaguar pfp
Jaguar
@jwo
1 reply
8 recasts
29 reactions
Sales pfp
Sales
@isx
1 reply
2 recasts
29 reactions
Galego pfp
Galego
@dle
Não estou encontrando meu gato, acho que ele foi dar um passeio pelo telhado
0 reply
0 recast
1 reaction
𝚐𝔪𝟾𝚡𝚡𝟾 pfp
𝚐𝔪𝟾𝚡𝚡𝟾
@gm8xx8
Emu3: Next-Token Prediction is All You Need Emu3 is a new suite of multimodal models trained through next-token prediction. It converts images, text, and videos into a discrete space and trains a single transformer with multimodal sequences. Emu3 surpasses models like SDXL, LLaVA-1.6, and OpenSora-1.2 in both generation and perception tasks, without using diffusion or compositional architectures. —Emu3 generates high-quality images from text input by predicting the next visual token, supporting different resolutions and styles. —Demonstrates strong understanding between vision and language, providing coherent text responses without relying on CLIP or a pretrained LLM. —Produces videos by sequentially predicting the next token, allowing for video extension and future event prediction without diffusion models. Emu3: https://huggingface.co/collections/BAAI/emu3-66f4e64f70850ff358a2e60f github: https://github.com/baaivision/Emu3 project page: https://emu.baai.ac.cn/about
1 reply
0 recast
22 reactions