code/docs/actor-3.md

Actor-3 — Better consistency

Actor-3 is the consistency-oriented MR-IQA-2 Actor. It was initialized from Qwen3.5-4B and trained for five epochs (1,455 optimizer updates). The language model was fully trainable; the vision encoder and visual aligner were frozen.

The training objective combines pairwise source/edited-image consistency with retained edit utility and loss-side KL (beta=0.02). Its preservation-first v9 prompt discourages semantic changes to subjects, objects, layout, text, composition, and unaffected regions.

The exact prompt contracts are published as:

• training prompt
• test prompt

Run deterministic single-image inference with:

python examples/actor_3_inference.py /absolute/path/to/input.jpg

To use an already downloaded checkpoint:

python examples/actor_3_inference.py /absolute/path/to/input.jpg \
  --model /absolute/path/to/actor-3 \
  --local-files-only

The script prints and optionally saves the raw completion plus the parsed reasoning.evidence, reasoning.solution, and rating fields.