Loading...
Loading...
Browse all stories on DeepNewz
VisitWhen will Black Forest Labs release their text-to-video models?
Q4 2024 • 25%
Q1 2025 • 25%
Q2 2025 • 25%
Q3 2025 • 25%
Official announcements from Black Forest Labs
Stable Diffusion Creators Launch FLUX.1 Text-to-Image Models with $31M Funding
Aug 1, 2024, 04:48 PM
Black Forest Labs, a new company founded by Robin Rombach, Patrick Esser, and Andreas Blattmann, the creators of Stable Diffusion, has launched a suite of state-of-the-art text-to-image models called FLUX.1. The suite includes FLUX.1[pro], available behind an API, and FLUX.1[dev], a 12-billion-parameter model available under both non-commercial and Apache 2.0 licenses. The models are designed to excel in text, composition, prompt following, image detail, and output diversity. Black Forest Labs has secured $31 million in funding to support the development of these models. The company aims to advance generative deep learning models for media and push the boundaries of creativity, efficiency, and diversity. The models have been released on platforms like HuggingFace and are available for use on Poe and replicate. The FLUX.1 models are claimed to have the strongest ELO scores and are expected to set new standards in the industry. Additionally, Black Forest Labs plans to release text-to-video models in the future.
View original story
Yes • 50%
No • 50%
Meta • 25%
Google • 25%
Stability AI • 25%
Other • 25%
The World Labs • 25%
Meshy AI • 25%
Aiuni AI • 25%
Meta 3D AI • 25%
Real-time editing • 25%
4K resolution support • 25%
New AI-generated effects • 25%
Other • 25%
Microsoft • 25%
Meta • 25%
Google • 25%
Other • 25%
RunwayML Gen-3 Alpha • 33%
Luma AI Keyframes • 33%
Google's VEO • 33%
Facebook • 25%
Instagram • 25%
TikTok • 25%
Other • 25%
Google • 25%
Spotter • 25%
Adobe • 25%
Other • 25%
OpenAI • 25%
Microsoft • 25%
Meta • 25%
Other • 25%
Yes • 50%
No • 50%
No • 50%
Yes • 50%
Less than 10,000 • 25%
More than 100,000 • 25%
50,001 to 100,000 • 25%
10,000 to 50,000 • 25%