Tweak
Change one knob in ComfyUI and update the run notes.
Kforge Labs automations
The automation loop keeps ComfyUI renders, workflow JSON, tracking cards, iteration logs, and promoted findings moving through one repeatable path.
Mental model
ComfyUI still owns creative iteration. The automation layer gives every render a traceable card and a durable log, so the next decision is based on what actually happened.
Change one knob in ComfyUI and update the run notes.
Export workflow JSON into the working folder.
Write the video beside the JSON with the same run identity.
Run /make-card to create the visual run summary.
Move stable patterns from the iteration log into findings.
Data contract
Three Text Multiline nodes are enough to connect ComfyUI, the repo tools, and the per-project evidence folder.
<working folder>/ LTX-Director_v04.json LTX-Director_v04.mp4 more JSONs and MP4s _AI/ card.png iterations.md
Absolute path to the project folder. This wins over the repo .env fallback.
Run summary plus a BASE (notes): section for what changed this time.
Post-render observations and scores like motion: 4/5, sync: 5/5, sharp: 4/5.
_AI/card.png is overwritten each run. Wire your NLE to it once and keep comparing.
_AI/iterations.md grows one row per unique workflow save, with duplicate runs filtered.
Per-project JSON, MP4, cards, and logs live outside the repo. Docs and findings live here.
Each model gets its own docs folder under docs/automations/; shared rules stay in CONVENTIONS.md.
Inside ComfyUI
Before rendering, update OVERLAY - INFO. After watching the video, update OVERLAY - FEEDBACK. The saved JSON becomes the source of truth for the card.
In the agent
/make-card finds the newest non-loop workflow JSON, extracts node parameters, writes the card, and appends the iteration log.
$ /make-card Reading newest workflow JSON... Writing _AI/card.png Appending _AI/iterations.md Card ready: /JOBS/scene/ComfyUI-working-folder/_AI/card.png
When evidence settles
When a knob behaves the same way across several runs, move the conclusion into the model's findings.md. The loop gets smarter because the docs shrink toward truth.
linear_quadratic with 8 steps is the current locked path.
euler and CFG 1.0 stay fixed while sweeping other knobs.