This commit introduces several new performance-oriented custom nodes and utilities:
- Added LTXV Multi Concat and LTXV Multi Concat (beta) for faster frame injection using latent inpainting logic.
- Refactored LTXV index resolution logic into ltxv_utils.py.
- Updated ImageListSampler to anchor edge frames properly and support output index normalization scaling via target_frames.
- Added metadata-based prompt extraction image loaders (LoadImageAndExtractPrompt, FolderImageAndExtractPrompt, and FolderImageMetadataByName).
- Included animation tracking and camera switcher nodes.
- LoadGifFrames: loads GIF via Pillow (no OpenCV/FFmpeg), deduplicates
identical frames using MD5 hash, outputs unique_frames batch + frame_map
JSON for reconstruction. Alpha channel composited over white background.
- RemapGifFrames: decompressor node that expands deduplicated processed
frames back to full sequence using frame_map.
- BatchToImageList: splits IMAGE batch [N,H,W,C] into list of N individual
frames so ComfyUI iterates the pipeline per-frame, avoiding RAM spikes
on VAE encode/decode with large GIF batches.
- js/load_gif_frames.js: upload widget for LoadGifFrames accepting .gif only.
New node that loads prompts from CSV files with dropdown selection.
CSV format: name,prompt,negative_prompt
Features dropdown selection of prompt names and outputs selected prompt and negative prompt.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Marco