Black Forest Labs – FLUX.1 open weights SOTA text to image model
Black Forest Labs has launched to develop generative deep learning models for media, securing $31 million in funding. Their FLUX.1 suite includes three model variants, outperforming competitors in image synthesis.
Read original articleBlack Forest Labs has officially launched, focusing on the development of advanced generative deep learning models for media, particularly in text-to-image synthesis. The organization aims to make generative AI accessible to a broad audience, enhancing public education and trust in these technologies. The team comprises experienced AI researchers and engineers known for their contributions to foundational generative models, including VQGAN and Stable Diffusion. They have successfully closed a Series Seed funding round of $31 million, led by Andreessen Horowitz, with participation from notable angel investors and follow-up investments from General Catalyst and MätchVC.
The newly released FLUX.1 suite includes three model variants: FLUX.1 [pro], FLUX.1 [dev], and FLUX.1 [schnell]. FLUX.1 [pro] offers top-tier performance for commercial applications, while FLUX.1 [dev] is an open-weight model for non-commercial use. FLUX.1 [schnell] is designed for local development and personal use, available under an Apache2.0 license. All models utilize a hybrid architecture with 12 billion parameters, improving performance and efficiency through innovative training methods.
FLUX.1 models set new benchmarks in image synthesis, outperforming competitors like Midjourney and DALL·E in various aspects, including visual quality and output diversity. The company plans to expand its offerings to include generative text-to-video systems in the future. Black Forest Labs is also actively hiring machine learning and backend engineers.
Related
AuraFlow v0.1: a open source alternative to Stable Diffusion 3
AuraFlow v0.1 is an open-source large rectified flow model for text-to-image generation. Developed to boost transparency and collaboration in AI, it optimizes training efficiency and achieves notable advancements.
VCs are still pouring billions into generative AI startups
Investments in generative AI startups reached $12.3 billion in H1 2023, focusing on early-stage ventures. Challenges include legal issues and rising costs, making profitability elusive for many companies.
Diffusion Training from Scratch on a Micro-Budget
The paper presents a cost-effective method for training text-to-image generative models by masking image patches and using synthetic images, achieving competitive performance at significantly lower costs.
The open weight Flux text to image model is next level
Black Forest Labs has launched Flux, the largest open-source text-to-image model with 12 billion parameters, available in three versions. It features enhanced image quality and speed, alongside the release of AuraSR V2.
GitHub Models: A new generation of AI engineers building on GitHub
GitHub has launched GitHub Models, providing developers access to advanced language models for AI experimentation, enhancing coding practices while ensuring privacy and security in development processes.
FLUX.1 [dev] (non-commercial, open weights, guidance distilled): https://fal.ai/models/fal-ai/flux/dev
FLUX.1 [schnell] (Apache 2.0, open weights, step distilled): https://fal.ai/models/fal-ai/flux/dev
FLUX.1 [pro] (closed source [only available thru APIs], SOTA, raw): https://fal.ai/models/fal-ai/flux-pro
Related
AuraFlow v0.1: a open source alternative to Stable Diffusion 3
AuraFlow v0.1 is an open-source large rectified flow model for text-to-image generation. Developed to boost transparency and collaboration in AI, it optimizes training efficiency and achieves notable advancements.
VCs are still pouring billions into generative AI startups
Investments in generative AI startups reached $12.3 billion in H1 2023, focusing on early-stage ventures. Challenges include legal issues and rising costs, making profitability elusive for many companies.
Diffusion Training from Scratch on a Micro-Budget
The paper presents a cost-effective method for training text-to-image generative models by masking image patches and using synthetic images, achieving competitive performance at significantly lower costs.
The open weight Flux text to image model is next level
Black Forest Labs has launched Flux, the largest open-source text-to-image model with 12 billion parameters, available in three versions. It features enhanced image quality and speed, alongside the release of AuraSR V2.
GitHub Models: A new generation of AI engineers building on GitHub
GitHub has launched GitHub Models, providing developers access to advanced language models for AI experimentation, enhancing coding practices while ensuring privacy and security in development processes.