Be the first to get access to upcoming FLUX Models.
We’re opening up the first FLUX Creator Program. We’re looking for a small group of creators already making standout work with FLUX.
You get:
• Early access to our upcoming models
• Amplification of your work via BFL’s channels
• Lots of credits
• Direct access to our engineering team
This is our first cohort, so spaces are limited.
Just launched the Steam page for our incremental Tower Defense game "Sir, We Have a Orc Problem" and got over 900 Wishlists in the first 24 hours. #gamedev#indiedev
https://t.co/huSyhGbJQv
BFL x @Forbes AI 50 list
A nod to our researchers and community pushing the pixel frontier, building open infrastructure for visual intelligence.
Congrats to this year’s AI 50 class
https://t.co/QK1hJDCUsL
Releasing FLUX.2 Small Decoder: a faster, drop-in replacement for our standard decoder.
→ ~1.4x faster
→ Lower peak VRAM - decode larger images without running out of memory
→ Minimal quality loss
→ Works with FLUX.2 out of the box
Especially impactful for real-time and larger resolutions pipelines.
Meet Z-Image-Lora: a specialized text-to-image model that's been turning heads. It's not just another image generator. This LoRA adapter fine-tunes a powerful base model, giving you precision control over specific visual styles. Perfect for creators who want consistency with flair.
Descent turns 30 years old today!
This innovative 3D shooter will actually play on a 486 with 4MB of RAM - talk about efficient memory usage! (I tried it)
@MatthewBerman But sounds really nice, currently just messing around how good can qwen3 4B can work with some tools in a telegram bot, sofar isngiod but still need lots of refinement when creating a mcp tool for img to img
“Local models and cloud models will work together.”
@ilblackdragon CEO of @NEARProtocol:
“Local models are great for tinkering and for simpler tasks, and their intelligence keeps improving.”
“But harder tasks can fall back to larger models running in the cloud.”
“Your agent might run simple things locally, while heavier workflows run remotely and confidentially.”
“It’s really about creating a seamless handoff between local and cloud.”