Enze Xie(@xieenze_jr):Day-0 Sol Engine + Sol-Attn for @video_rebirth HyperFlow. 8-step, data-free distill of MiniMax-H3. One LoRA: T2V / FL / Ref. Sol-Attn is the training-free sparse path — near-lossless vs dense attention, no extra fine-tune. On 8×B200, same HyperFlow recipe before vs after Sol: T2V 5s 9.89s → 2.75s (3.6×) T2V 15s 36.93s → 11.85s (3.1×) Ref 5s 15.27s → 2.97s (5.1×)

2026.09.19 02:26

Day-0 Sol Engine + Sol-Attn for @video_rebirth HyperFlow. 8-step, data-free distill of MiniMax-H3. One LoRA: T2V / FL / Ref. Sol-Attn is the training-free sparse path — near-lossless vs dense attention, no extra fine-tune. On 8×B200, same HyperFlow recipe before vs after Sol: T2V 5s 9.89s → 2.75s (3.6×) T2V 15s 36.93s → 11.85s (3.1×) Ref 5s 15.27s → 2.97s (5.1×)

VIDEO REBIRTH@video_rebirth

2026.09.18 18:04

We're open-sourcing H3 HyperFlow. A data-free flow self-distillation technology built on @MiniMax_AI H3. No external training data. Significantly reduces inference cost while preserving frontier model quality. Full demo:

轉發到社區