SANA-1.6B
An efficient text-to-image diffusion model introduced by NVIDIA, with approximately 1.6 billion parameters. It is designed to deliver high generation efficiency and image quality.
Timeline (last 90 days)
With SANA-1.6B as the base model and ImageReward as the reward model, SatisDive improved the worst candidate reward by up to 0.70 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 (2)
With SANA-1.6B as the base model and ImageReward as the reward model, SatisDive improved the worst candidate reward by up to 0.70 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%