nodes/gregtee2-ComfyUI_VideoChunkTools
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2 Commits 1 Branch 0 Tags
main
Commit Graph
2 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Greg 277f12c213 feat: Per-chunk text conditioning via ChainTextEmbeds node 
- New ChainTextEmbeds node: chains up to 8 WanVideoTextEncode outputs
  into an ordered TEXT_EMBED_SEQUENCE for per-chunk prompting
- WanChunkedI2VSampler: new optional text_embed_sequence input
  overrides single text_embeds when connected
- Chunk N uses embed N from the sequence; last embed repeats for
  any extra chunks beyond the sequence length
- Console output shows which embed index is used per chunk
- README updated with per-chunk prompting workflow diagram
 2026-02-23 11:56:01 -08:00
Greg 7bb60125b9 feat: Initial release — 9 nodes for chunked long video generation 
Core nodes (7): BlendVideoChunks, BlendLatentChunks, ConcatVideoChunks,
ExtractVideoChunk, GetFrameByIndex, GetFrameRange, VideoChunkPlanner

Wan-specific nodes (2): WanChunkedI2VSampler (all-in-one with FLF/multi-keyframe),
WanVideoChunkCalculator

Rolling-reference approach solves context window reversal in I2V models.
 2026-02-23 10:21:15 -08:00