nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
872 Commits 343 Branches 8 Tags
2cfcb7b85fc01238574bdd1973c6cb798395ff9b
Commit Graph
4 Commits
Author SHA1 Message Date
Will LinandClaude Fable 5 539884b9ba [bugfix]: keep kandinsky5 example text encoders on GPU 
text_encoder_cpu_offload=True makes the Qwen encoder compute on CPU, where
flash-attn has no kernels; with flash_attn installed both examples crash in
the first text-encoding forward. The offloaded path only worked in envs
without flash_attn via the silent SDPA fallback.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-07 14:35:48 -07:00
leffff 4b0206d82a [feat] add support for Kandinsky 5 Pro, Lite I2V 2026-07-07 14:35:48 -07:00
leffff ed1fbee9b0 [feat] add support for Kandinsky5 I2V 2026-07-07 14:35:48 -07:00
leffff 6de9d6ee87 [misc] add skeleton for Kandinsky5 I2V pipeline 2026-07-07 14:35:48 -07:00