JerryZhou54 df7381e2b0 Support sampling from the full timestep range in dmd_forward & faker_score_forward when the output video is only generated by high noise generator

2025-10-13 21:10:34 +00:00

..

dataset/vidprom

[self-forcing] [3/n] Text embed only preprocessing (#797)

2025-09-13 14:03:53 -07:00

distill

Support sampling from the full timestep range in dmd_forward & faker_score_forward when the output video is only generated by high noise generator

2025-10-13 21:10:34 +00:00

inference

[Feature] Add wan2.2 5b i2v (#760)

2025-08-28 18:15:59 -07:00

training

checkpoint

2025-10-04 23:56:36 +00:00