lora for the snail character at different ages trained successfully by Ciprian (alberto-ciprian); test prompts + parameters on Google Drive; compositing tests started, facial expressions need improvement
-
2
Traceability
Trained images to be tagged + linked to the snail character in Yamdu for traceability (naming-schema, provenance)
-
3
Tool selection
rai-crits selected over edit-mind for metadata extraction: richer semantic output (audio transcription with speaker diarization, named entity recognition, scene analysis), shot-block granularity, human-readable IDs, MAM integration
-
4
Shot list
Tim (tim-deussen) produced a shot list mapping archive footage to script locations with timecodes + production notes; flags for archive clearance, brand/logo, likeness, music, + human validation of AI metadata
Action 1
5
Drive structure
Google Drive folder structure + workflow documentation aligned to the MovieLabs ontology (omc-ontology); JSON, JSON-LD + TTL exports carry scene + character identifiers
John Hobbs (john-hobbs) demoed: AWS S3 + Neo4j graph database, versioning by humans + machines, comments as first-class assets, M2M API for agents; positioned as alternative to Frame.io
-
7
Amici
Ahsan Mallick introduced Amici: AI governance platform for film/TV, launched an AI competency course based on the Alan Turing framework
-
8
Best practices
Identifier best-practices folder planned for interoperability