Clarify upstream NEvo attribution

Condense Intended Use / Out-of-scope / Risks to a single paragraph

License under CC BY-NC 4.0; add Intended Use / Out-of-scope / Risks section

Sync from GitHub: save_video fps default 12 + README fps/batch docs + fix params (mutation/elite/video defaults)

Expose encoder input resolution as score_size (default 224)

README quickstart: also save out.best.image

Double default max_evals (400/200) + README consistency + fix run_roi_samples

Default seed to None (random each run); expose used seed in metadata

~2.2x faster search (drop CPU PIL->tensor stall), live progress bar, README seed

Per-stage eval budgets image_max_evals/video_max_evals (200/100)

Fast default image/video kwargs + lighter default generations (10/5)

Split into image_num_generations (50) / video_num_generations (25)

Replace num_candidates/max_evals with num_generations (population_size + num_generations)

Replace num_rounds with population_size (default 20), matching clean_search

Flag work-in-progress at top of model card

Two-stage pipeline (image search then motion search) with per-stage budgets

Progress bar option for the genetic search

Off-the-shelf custom_pipeline bootstrap + README

Quickstart on defaults + Faster run block; drop seed_prompts

Double-column gallery, drop How-it-works, swappable placeholder models

Simplify How-it-works, drop gallery caption column, halve gallery videos

Sync from GitHub: install instructions, updated gallery videos, deps

Quickstart one-line video save + export helper

ROI-enhanced search space + docs; EBA caption

Model card: EBA example, drop pct, fsaverage5 note

Model card: gallery + website + citation

Publish self-contained NEVO stimulus-synthesis pipeline + model card

initial commit