AI Toolkit Adds MiniMax H3 Text-to-Video and Image-to-Video Training

ComfyUI Wikinews

Ostris AI Toolkit now supports training MiniMax H3 T2V and I2V LoRAs, with NVFP4 quantization and VAE gradient checkpointing for consumer GPUs.

댓글

GitHub로 로그인하고 토론에 참여하세요.

댓글을 불러오는 중…
AI Toolkit Adds MiniMax H3 Text-to-Video and Image-to-Video Training | ComfyUI Wiki