Results for “stable-diffusion”

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Train reinforcement learning agents using PPO, SAC, DQN, TD3, DDPG, and A2C algorithms with a scikit-learn-like API. Supports custom Gymnasium environments, vectorized environments, callbacks, and model persistence.