FLUX.1-dev
A high-quality text-to-image diffusion model released by Black Forest Labs. The developer version (dev) supports both research and commercial application scenarios.
Timeline (last 90 days)
PageRank over the lineage shows that the most depended-upon model on the entire Hugging Face Hub is black-forest-labs/FLUX.1-dev, a non-commercial model.
If Black Forest Labs changed FLUX.1-dev to Apache-2.0, after copying the 43,700-model family with GRAPH.COPY and recomputing, 27,592 models would still retain the non-commercial tag, because their own cards copied FLUX's license and uploaders would need to modify them manually.
On the Pick-a-Pic dataset using DreamSim as the diversity metric, with FLUX.1-dev as the base model and HPSv3 as the reward model, SatisDive improved the worst candidate reward by up to 0.43 compared to FK steering.
SatisDive requires no training and intervenes only at inference time, possessing plug-and-play characteristics; the paper has been validated across multiple combinations including FLUX.1-dev, SANA-1.6B, HPSv3, and ImageReward.
All Facts (4)
PageRank over the lineage shows that the most depended-upon model on the entire Hugging Face Hub is black-forest-labs/FLUX.1-dev, a non-commercial model.
50%UnverifiedOn the Pick-a-Pic dataset using DreamSim as the diversity metric, with FLUX.1-dev as the base model and HPSv3 as the reward model, SatisDive improved the worst candidate reward by up to 0.43 compared to FK steering.
50%UnverifiedSatisDive requires no training and intervenes only at inference time, possessing plug-and-play characteristics; the paper has been validated across multiple combinations including FLUX.1-dev, SANA-1.6B, HPSv3, and ImageReward.
50%UnverifiedIf Black Forest Labs changed FLUX.1-dev to Apache-2.0, after copying the 43,700-model family with GRAPH.COPY and recomputing, 27,592 models would still retain the non-commercial tag, because their own cards copied FLUX's license and uploaders would need to modify them manually.
50%