FLUX.1
A high-quality image generation diffusion model released by Black Forest Labs. It has ranked among the most highly starred open-source models on Hugging Face.
Timeline (last 90 days)
FLUX.1 and Kontext, two models released by Black Forest Labs, use flow matching instead of traditional diffusion models for image generation and editing.
FLUX.1 can be accessed either via Black Forest Labs' hosted API or deployed locally.
Rectified Flow is a specific implementation of flow matching that straightens the path between the source distribution and the target distribution into a straight line, enabling fewer integration steps and higher generation efficiency.
Current mainstream open-source image generation models such as Stable Diffusion XL and FLUX.1 typically have parameter counts in the range of billions to tens of billions, with inference VRAM requirements often exceeding 12GB.
The model received approximately 15,100 likes, surpassing FLUX.1 (approximately 14,700).
All Facts (4)
FLUX.1 and Kontext, two models released by Black Forest Labs, use flow matching instead of traditional diffusion models for image generation and editing.
50%UnverifiedFLUX.1 can be accessed either via Black Forest Labs' hosted API or deployed locally.
50%UnverifiedRectified Flow is a specific implementation of flow matching that straightens the path between the source distribution and the target distribution into a straight line, enabling fewer integration steps and higher generation efficiency.
50%UnverifiedCurrent mainstream open-source image generation models such as Stable Diffusion XL and FLUX.1 typically have parameter counts in the range of billions to tens of billions, with inference VRAM requirements often exceeding 12GB.
50%