automatic

mirror of https://github.com/vladmandic/automatic synced 2026-09-03 11:30:46 +02:00

Files

T

CalamitousFelicitousness a04ba1e482 feat(api): add missing caption API parameters for UI parity

Add prompt field to VQA endpoint and advanced settings to OpenCLIP endpoint
to achieve full parity between UI and API capabilities.

VLM endpoint changes:
- Add prompt field for custom text input (required for 'Use Prompt' task)
- Pass prompt to vqa.interrogate instead of hardcoded empty string

OpenCLIP endpoint changes:
- Add 7 optional per-request override fields: min_length, max_length,
  chunk_size, min_flavors, max_flavors, flavor_count, num_beams
- Add get_clip_setting() helper for override support in openclip.py
- Apply overrides via update_interrogate_params() before interrogation

All new fields are optional with None defaults for backwards compatibility.

2026-02-11 02:47:40 +00:00

api.py

feat(api): add caption API endpoints and documentation

2026-02-11 02:47:40 +00:00

control.py

add xyz and script support to control api

2025-11-23 13:07:42 -05:00

docs.py

update swagger docs

2025-10-07 08:21:05 -04:00

endpoints.py

feat(api): add missing caption API parameters for UI parity