Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-02 11:00:46 +02:00
Code Issues Packages Projects Releases Wiki Activity
13,896 Commits 3 Branches 34 Tags
4bdda6d91afdf875c1455a54d846bd34597b2021
Commit Graph

83 Commits

Author SHA1 Message Date
Vladimir Mandic 51a0eaaa21 add experimental openai interface 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-07-02 14:36:44 +02:00
Vladimir Mandic 1cf715fac2 add gemma-4-unified, tensor-compressed, qat 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-06-12 15:15:16 +02:00
Vladimir Mandic d2d9f7caea captioning improvements and cleanup 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-29 21:10:56 +02:00
Vladimir Mandic 60e6c37e24 fix script params 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-22 18:28:22 +02:00
Vladimir Mandic 082498e6bd prompt-enhance-v2 with steering 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-22 16:58:23 +02:00
Vladimir Mandic c8d6fd5cf8 Revert "much stricter ruff linting" 
This reverts commit 310dbf1574.
 2026-05-11 08:13:57 +02:00
Vladimir Mandic 310dbf1574 much stricter ruff linting 
Co-authored-by: Copilot <copilot@github.com>
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-11 07:15:37 +02:00
Vladimir Mandic 57f5bf5bd5 add missing js files 
Co-authored-by: Copilot <copilot@github.com>
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-02 10:56:52 +02:00
Vladimir Mandic 823058b15a add prompt-enhance info to metadata 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2026-05-02 10:41:01 +02:00
vladmandic 40e550f1c3 add timer info 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-04-23 12:49:41 +02:00
vladmandic b103c2c1ff add gemma-4 heretic variant 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-04-12 19:06:08 +02:00
vladmandic 91bba59c0d fix lint 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-04-12 19:06:08 +02:00
vladmandic 14ba5e4ce7 update nudenet 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-04-09 13:48:54 +02:00
CalamitousFelicitousness 0e5d351099 add google gemma-4-e2b and gemma-4-e4b support 
- add to prompt enhance models, img2img, and models_cls
- add to vlm/caption models
- update _load_gemma class selection for gemma 4
- bump transformers pin to 5.5.0.dev for gemma4 architecture support
 2026-04-09 03:21:50 +01:00
vladmandic b5e9fbc7b3 reorganize scripts/extensions 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-27 14:00:46 +01:00
awsr c3cce0ad76 PEP 484 scripts directory 2026-03-25 16:56:28 -07:00
vladmandic 9eced4ff86 cleanup 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-13 15:05:47 +01:00
vladmandic 6821d92a92 use aux for prompt enhance 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-13 13:05:34 +01:00
vladmandic 242325c11d merge: scripts/prompt_enhance.py 2026-03-13 13:04:35 +01:00
vladmandic 9df9ed1b05 update gemini models 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-04 07:31:36 +01:00
vladmandic 04757adc78 lint 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-02 11:09:15 +01:00
vladmandic 1ddd0bf33a add gemini to prompt enhance 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-03-02 11:01:17 +01:00
Vladimir Mandic e5c494f999 cleanup logger 2026-02-19 11:09:13 +01:00
Vladimir Mandic a3074baf8b unified logger 2026-02-19 09:46:42 +01:00
CalamitousFelicitousness 86744ebd76 feat(prompt-enhance): add Top-K and Top-P sampler controls 
Add Top-K and Top-P sampling parameters to match VQA capabilities:
- Top-K: 0-100 (default 0 = disabled)
- Top-P: 0.0-1.0 (default 0 = disabled)

Parameters are only passed to the model when > 0, matching VQA behavior.
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness e881faa2fb feat(vlm): align default generation settings 
Update default settings for both Prompt Enhance and VQA:
- max_tokens: 512 (prompt enhance)
- do_sample: True
- temperature: 0.8

These defaults provide better output quality with more creative
variation while maintaining coherent results.
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness de1d520929 fix(prompt-enhance): align with VQA approach and fix multiple issues 
Thinking mode alignment with VQA:
- Expand is_thinking_model() detection (moondream, mimo patterns)
- Use manual </think> tag approach instead of enable_thinking parameter
- Handle prefill via string concatenation, not assistant message

Bug fixes:
- Fix max_new_tokens (was input_len + tokens, now just tokens)
- Fix vision toggle not disabling vision (wrap image processing in check)
- Fix VL processor error when vision disabled (explicit text= parameter)
- Add error handling when vision enabled but no image provided

Debug logging consistency with VQA:
- Add model_class to entry debug
- Add input_ids_shape to tokenization debug
- Rename raw -> response_before_clean, response -> response_after_clean

UI improvements:
- Make Enhanced prompt textarea scrollable (max_lines=12)
- Remove redundant mode variable from logging
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness d1a08ec801 fix(prompt-enhance): add Kanvas image support and debug logging 
Add fallback to ui_control_helpers.input_source when Gradio image
component is empty, which occurs when Kanvas is active (replaces
gr.Image with gr.HTML).

Also standardize debug logging:
- Add debug at enhance() entry, chat template, tokenization
- Change shared.log.trace() calls to use debug_log() for consistency
- All debug output controlled by SD_LLM_DEBUG environment variable
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness 5f1fbbaeca ui(prompt): add descriptive placeholders to text fields 
Clarify purpose of empty fields with placeholder text:
- System prompt: explains built-in instructions used when empty
- Prefix/suffix: describe where text is added to result
- Output: indicates where enhanced prompt appears
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness 7c8f7fd296 feat(prompt): add prefill and thinking mode handling 
Add prefill text support and proper thinking tag handling:
- Prefill text input to pre-fill start of model response
- Keep Prefill toggle to retain/remove prefill from output
- Keep Thinking Trace toggle to format <think> tags as readable output
- Proper <think> tag cleanup: strip or format as "Reasoning:/Answer:"
- Support for prefill + thinking combination via keep_think_block_open()

Chat template uses continue_final_message=True when prefill provided,
allowing model to continue from the prefill text naturally.
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness a77173881f feat(prompt): add vision/reasoning symbols and vision toggle 
Add visual capability indicators and user control for image input:
- Vision symbol (eye icon) for VL-capable models in dropdown
- Reasoning symbol (lightbulb) for thinking-capable models
- "Use vision" checkbox to control image input for enhancement
- Toggle dims and unchecks when non-VL model selected
- Vision auto-enables when switching to VL model

Also:
- Rename "Do sample" to "Use samplers" for consistency with VQA
- Add tooltips/hints for all prompt enhance UI elements
- Add CSS styling for dimmed vision toggle appearance
 2026-01-12 00:17:20 +00:00
CalamitousFelicitousness 73588c2000 Comment tweaks 2025-10-26 06:52:39 +00:00
CalamitousFelicitousness 33f335a98c VQA class fix f-statement fix 2025-10-26 06:39:05 +00:00
CalamitousFelicitousness 1ac4214379 fix cls_name variable 2025-10-26 06:20:14 +00:00
CalamitousFelicitousness 80bb331169 Prompt enhance resizing and Qwen VL fix 2025-10-26 06:01:33 +00:00
CalamitousFelicitousness c72d993ff4 Prompt enhance update 
Added Qwen3-VL models to prompt enhance
Added Qwen2.5-VL and Glitter Gemma 4B to
    img2img prompt enhance
 2025-10-26 03:12:10 +00:00
Vladimir Mandic 5d0a3e5e8a fix microsoft-florence 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-10-01 10:58:52 -04:00
Vladimir Mandic 175e9cbe29 cleanup/refactor state history 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-09-12 16:12:45 -04:00
Vladimir Mandic 33b92d9ad9 improve prompt enhance system prompt 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-08-12 15:09:08 -04:00
Vladimir Mandic 863e172aad add Qwen/Qwen2.5-VL-3B-Instruct 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-08-12 15:09:08 -04:00
Vladimir Mandic 6312b3d0ac add Qwen3-4B-Instruct-2507 llm and Flash-FlowMatch scheduler 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-08-11 16:35:16 -04:00
Vladimir Mandic 4b74fd26b5 redesign gpu monitor 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-08-07 13:56:13 -04:00
Vladimir Mandic e4de0baa6f prompt enhance improve tokenizer handler 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-27 14:22:24 -04:00
Vladimir Mandic fd722311db css and logging tweaks 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-27 08:17:41 -04:00
Vladimir Mandic 287c3600d7 torch compile for llm 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-20 12:07:30 -04:00
Vladimir Mandic 0f2f164245 add smollm3, add auraflow-0.2, enable taesd for auraflox 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-14 07:24:20 -04:00
Vladimir Mandic b625884031 add gemma3n to caption/vlm and promptenhance 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-07 10:01:02 -04:00
Vladimir Mandic c4d9338d2e major refactoring of modules 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-03 09:18:38 -04:00
Vladimir Mandic 7447a79b46 update requirements 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-27 17:58:18 -04:00
Disty0 17df7ba83b Cleanup whitespace 2025-05-26 02:41:29 +03:00