daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Record direct FL2VA smoke preview

Browse source
This commit is contained in:
Daniel Maddern 2026-08-13 16:06:33 +07:00
parent 55e2073784
commit 82e8ddecbc
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
PARITY.md
View file

@ -189,6 +189,7 @@ gate and is exact.
| Beta/RES sampler | Yes | H3 replay is bit-exact for all 12 captured sampler calls and RES update is bit-exact from captured denoised; direct raw-output to model-wrapper denoised conversion retains small BF16/state boundary deltas |
| Video VAE decoder | Yes | Same final sampled latent decoded through direct VAE versus Comfy PNG frames: mean abs pixel delta `0.0833898`, max `6` |
| Audio VAE/decode/mux | No | Preview intentionally produces video only |
| End-to-end prompt-only FL2VA preview | Yes | Direct 320x192x22 dragon smoke video generated with Sage2 at `/home/daniel/StoryStudioAssets/H3-output/h3-blackwell-runtime/direct-fl2va-dragon-e2e-55e2073.mp4`; seed-exact Comfy initial AV state parity is not implemented |
| Full Ref2VA | No | References, vision conditioning, VAE encode, audio, and muxing are unimplemented |
## Remaining Gates, In Dependency Order
@ -198,8 +199,9 @@ unless the checkpoint, Comfy version, prompt, or backend changes.
1. **Final video latent layout.** Compare direct `unpatchify_video` output
with Comfy before entering the sampler.
2. **End-to-end FL2VA preview.** Generate the reference dragon only after
gates 1-8 pass. Compare its raw final latent first, then video.
2. **Seed-exact prompt-only initialization.** Replace direct preview's local
`torch.manual_seed` video-only noise setup with Comfy-equivalent joint AV
initial latent generation before claiming identical seed output.
3. **Feature/performance work.** Only then add audio, Ref2VA/reference paths,
Sage3, CUDA graphs, and multi-GPU execution.