Commit Graph

34 Commits (a04ba1e4822a106fba21a408f4a191cefdbdfc90)

Author SHA1 Message Date
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
CalamitousFelicitousness f431141d2f feat(api): add LLM generation parameters to VQA endpoint
Add optional LLM generation parameters to the VQA API request model,
allowing per-request override of settings:

- max_tokens, temperature, top_k, top_p, num_beams, do_sample
- thinking_mode, prefill, keep_thinking, keep_prefill

Changes:
- Add 10 new optional fields to ReqVQA model with descriptive docs
- Update get_kwargs() to support per-request overrides via singleton
- Add helper functions get_keep_thinking(), get_keep_prefill()
- Update post_vqa endpoint to pass generation kwargs
- Add _generation_overrides instance variable to VQA class
2026-02-11 02:47:40 +00:00
CalamitousFelicitousness ec7934799e feat(api): add caption API endpoints and documentation
Add comprehensive caption/interrogate API with documentation:

- GET /sdapi/v1/interrogate: List available interrogation models
- POST /sdapi/v1/interrogate: Interrogate with OpenCLIP/BLIP/DeepDanbooru
- POST /sdapi/v1/vqa: Caption with Vision-Language Models (VLM)
- GET /sdapi/v1/vqa: List available VLM models
- POST /sdapi/v1/vqa/batch: Batch caption multiple images
- POST /sdapi/v1/tagger: Tag images with WaifuDiffusion/DeepBooru

Updates:
- Add detailed docstrings with usage examples
- Fix analyze_image response parsing for Gradio update dicts
- Add request/response models for all endpoints
2026-02-11 02:47:40 +00:00
vladmandic d9a2a21c8c add sampler api endpoints
Signed-off-by: vladmandic <mandic00@live.com>
2026-02-04 13:08:31 +01:00
vladmandic 7bd04e0b5c add /detailers api endpoint
Signed-off-by: vladmandic <mandic00@live.com>
2025-12-06 12:33:52 +01:00
Vladimir Mandic 72a9094b42 better model version detect and experimental pydantic v2
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-04 12:41:40 -04:00
Vladimir Mandic 2318f97991 manual set dtype via api
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-08-14 15:35:50 -04:00
Vladimir Mandic 2aa917b58e add /sdapi/v1/modules endpoint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-08-12 15:09:08 -04:00
Vladimir Mandic 73049f7bb8 add load-checkpoint api endpoint and test all models script
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-08-09 14:06:54 -04:00
Vladimir Mandic b2a52a146b fix ansi controle output and add model locking
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-06 12:50:09 -04:00
Vladimir Mandic e8b5ea3847 major refactor: remove backend original
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-05 13:16:46 -04:00
Vladimir Mandic 42b3e08e65 Control add setting to run hires with or without control
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-25 18:43:29 -04:00
Vladimir Mandic f8977d2f01 add /sdapi/v1/controlnets api endpoint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-25 15:54:43 -04:00
Vladimir Mandic 3d52e3fe9f add /sdapi/v1/lora endpoint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-25 10:54:02 -04:00
Vladimir Mandic 78e22350b9 add api get-checkpoint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-07 10:31:06 -04:00
Vladimir Mandic 57da399a1e fix api checkpoint list
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-29 17:20:29 -04:00
Vladimir Mandic 10fb362bdc server state history
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-25 12:25:30 -04:00
Vladimir Mandic b5031a5eba lora modularize code
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-01 13:39:47 -04:00
Vladimir Mandic dbfd59434f add gemma3
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-15 15:30:57 -04:00
Vladimir Mandic e95bd93f67 caption ui redesign
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 12:57:19 -05:00
Vladimir Mandic 2963ce127c refactor interrogate/caption
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-01 15:40:19 -05:00
Vladimir Mandic 654f44f66f refactor interrogate/analyze/vqa code
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-01 11:47:20 -05:00
Vladimir Mandic 6aa7a4707e modules.lora full integration
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-11-29 09:39:38 -05:00
Vladimir Mandic 2e08a26d53 add latent history
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-08 09:23:16 -04:00
Vladimir Mandic 3bbcc33181 add detailer
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-07 09:32:56 -04:00
Vladimir Mandic 04a5071249 face-hires -> detailer refactor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-06 11:23:33 -04:00
Vladimir Mandic 9bc217644d improve metadata parser 2024-06-06 11:24:31 -04:00
Vladimir Mandic 1227e76128 initial control api draft 2024-03-26 19:30:31 -04:00
Vladimir Mandic 902f02300d add vqa api 2024-03-26 09:24:01 -04:00
Vladimir Mandic 1b44a16a4e merge process and interrogate, add exif handler 2024-03-03 13:36:10 -05:00
Vladimir Mandic 537170fa2d fix api info endpoint 2024-02-28 11:11:48 -05:00
Vladimir Mandic 19e5062fa8 fix interrogate api 2024-02-10 09:13:07 -05:00
Vladimir Mandic b79d8ea6c3 cleanup api model defs 2024-01-28 10:25:26 -05:00
Vladimir Mandic 7e447222a1 refactor api 2024-01-28 10:13:09 -05:00