digital-garbageandClaude Sonnet 5.5 1fc5d99dcc feat: MiniMax H3 Reference to Video works text-only; with no picture a plain stand-in of the Width/Height shape feeds the size chain (found on a real GPU) ...

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-15 15:03:52 +03:00

..

tests

revert: H3 decode in one piece showed a tile grid (the decoder is trained on 256px tiles); back to ComfyUI's own tiling, tooltip says so

2026-10-07 15:01:07 +03:00

__init__.py

feat: H3 decode logs where its time goes: picture vs sound seconds, VAE precision, and whether the VAE was fully on the GPU

2026-10-07 15:26:31 +03:00

anchor.py

feat(v5): H3 second pass as graph -- upscaler loader, latent resample, typed pass-2 schedule

2026-09-27 17:49:39 +03:00

latent_upscaler.py

feat(v5): H3 second pass as graph -- upscaler loader, latent resample, typed pass-2 schedule

2026-09-27 17:49:39 +03:00

pipeline.py

feat: MiniMax H3 Reference to Video works text-only; with no picture a plain stand-in of the Width/Height shape feeds the size chain (found on a real GPU)

2026-10-15 15:03:52 +03:00

prompt_layout.py

feat(v5): prompt markup for H3 -- (word:1.5), [phrase@t0-t1], [a|b]

2026-09-27 18:11:51 +03:00

rope.py

feat: taste steering + taste attention learn from ratings; a failing wrapper no longer re-runs sampling

2026-09-27 18:31:10 +03:00

rows.py

fix: DynaShift and taste guidance read the step from ComfyUI's positional call; they never steered

2026-09-27 18:53:51 +03:00

streams.py

fix: LTX — tiled decode asked the way comfy asks it, picture found for ALG/DynaShift/guidance (shared av_video_stream), odd sizes said

2026-10-03 10:30:37 +03:00

vae_decode.py

revert: H3 decode in one piece showed a tile grid (the decoder is trained on 256px tiles); back to ComfyUI's own tiling, tooltip says so

2026-10-07 15:01:07 +03:00