LogoThread Easy
  • 探索
  • 線程創作
LogoThread Easy

Twitter 線程的一站式夥伴

© 2025 Thread Easy All Rights Reserved.

探索

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

Big news: Flux 2 is here ✨

The team at @bfl_ml have once again shipped some incredible image generation and editing models. 

It's great at complex, multi-part edits. 

I uploaded this photo and asked "make it anime style, add a16z x Fal x BFL, and blur out the background."

Big news: Flux 2 is here ✨ The team at @bfl_ml have once again shipped some incredible image generation and editing models. It's great at complex, multi-part edits. I uploaded this photo and asked "make it anime style, add a16z x Fal x BFL, and blur out the background."

@bfl_ml I've been running it on @fal - so I was very happy to have a picture to test with @gorkem, @nina_gerov, @robrombach, and @andi_blatt 😅 I'll be sharing results of LoRA training soon. In the meantime - worth checking out this chart! 👀

avatar for Justine Moore
Justine Moore
Tue Nov 25 19:08:22
> So you could imagine that the deployment itself will involve some kind of a learning trial and error period. It's a process, as opposed to, you drop the finished thing.

> So you could imagine that the deployment itself will involve some kind of a learning trial and error period. It's a process, as opposed to, you drop the finished thing.

Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.

avatar for Omar Khattab
Omar Khattab
Tue Nov 25 19:02:55
> So you could imagine that the deployment itself will involve some kind of a learning trial and error period. It's a process, as opposed to, you drop the finished thing.

> So you could imagine that the deployment itself will involve some kind of a learning trial and error period. It's a process, as opposed to, you drop the finished thing.

Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.

avatar for Omar Khattab
Omar Khattab
Tue Nov 25 19:02:55
RT @bfl_ml: FLUX.2 is here - our most capable image generation & editing model to date.

Multi-reference. 4MP. Production-ready. Open weigh…

RT @bfl_ml: FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weigh…

Partner at a16z & AI enthusiast. Investor in @cursor_ai, @udiomusic, @replicate, @hedra_labs, @MistralAI, @character_ai, @tabulario, @_hex_tech, @labelbox, ...

avatar for Matt Bornstein
Matt Bornstein
Tue Nov 25 18:55:51
RT @antoine_moyroud: @dwarkesh_sp @swyx and @FanaHOVA could you please align your publishing calendars - I don’t have that much timeeee htt…

RT @antoine_moyroud: @dwarkesh_sp @swyx and @FanaHOVA could you please align your publishing calendars - I don’t have that much timeeee htt…

achieve ambition with intentionality, intensity, & integrity - @dxtipshq - @sveltesociety - @aidotengineer - @latentspacepod - @cognition + @smol_ai

avatar for swyx
swyx
Tue Nov 25 18:55:43
RT @latentspacepod: From years as a Stanford professor and building ImageNet, the project that catalyzed the deep learning revolution, Fei-…

RT @latentspacepod: From years as a Stanford professor and building ImageNet, the project that catalyzed the deep learning revolution, Fei-…

achieve ambition with intentionality, intensity, & integrity - @dxtipshq - @sveltesociety - @aidotengineer - @latentspacepod - @cognition + @smol_ai

avatar for swyx
swyx
Tue Nov 25 18:55:39
  • Previous
  • 1
  • More pages
  • 2371
  • 2372
  • 2373
  • More pages
  • 5635
  • Next