AI/sdnext
1
0
Fork 0
mirror of https://github.com/vladmandic/sdnext.git synced 2026-01-27 15:02:48 +03:00
Code Activity
12,229 Commits 3 Branches 28 Tags
dev
Commit Graph

427 Commits

Author SHA1 Message Date
vladmandic
a7c32caae3 relocate all jsons to data 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-24 13:54:40 +01:00
CalamitousFelicitousness
becb19319d refactor(caption): unify tagger settings and reorganize Caption Tab UI 
Consolidate WD14 and DeepBooru tagger settings into unified options:
- Merge wd14_general_threshold + deepbooru_score_threshold → tagger_threshold
- Merge wd14_include_rating + deepbooru_include_rating → tagger_include_rating
- Rename interrogate_score → tagger_show_scores
- Rename tagger_escape → tagger_escape_brackets
- Rename CLiP → OpenCLiP in caption type choices

UI reorganization:
- Add Interrogate tab to Caption Tab with default caption type selector
- Move interrogate_offload to Model Offloading section as "Offload caption models"
- Hide Interrogate settings section (all settings now in Caption Tab UI)
- Update locale_en.json for OpenCLiP naming

Code improvements:
- DeepBooru tag_multi() now accepts same parameters as WD14 for unified interface
- Fix setting references in interrogate.py for consolidated settings
- Add comprehensive tagger test suite (cli/test-tagger.py)
 2026-01-21 11:56:07 +00:00
Oleksandr Liutyi
9e23e53340 FLUX.2-klein SDNQ Cover images 2026-01-18 15:29:39 +00:00
Vladimir Mandic
6f5e576ea7 Merge pull request #4556 from CalamitousFelicitousness/feat/f2preq-ref 
feat(flux2-klein): add SDNQ pre-quantized model support and reference images
 2026-01-18 07:14:23 +01:00
CalamitousFelicitousness
983e396f64 docs(i18n): improve LoRA settings hints and labels 
- Add detailed hints explaining LoRA fuse behavior and model reload warning
- Add hints for force reload, diffusers fuse, and quantization precision options
- Improve clarity of auto-apply tags and hash metadata hints
- Comment out unimplemented lora_quant setting
 2026-01-18 03:57:43 +00:00
CalamitousFelicitousness
33ee04a9f3 feat(flux2-klein): add SDNQ pre-quantized model support and reference images 
- Add Transformers v5 tokenizer compatibility fix for SDNQ Klein models
  Downloads missing vocab.json, merges.txt, tokenizer_config.json from
  Z-Image-Turbo when needed
- Detect SDNQ repos and disable shared text encoder to use pre-quantized
  weights from the SDNQ repo instead of loading from shared base model
- Update reference-quant.json with correct preview images and metadata
  for Klein SDNQ models
- Update reference-distilled.json with correct cfg_scale (1.0) for
  distilled Klein models per official HuggingFace documentation
- Add 6 Klein model preview images
 2026-01-17 21:36:44 +00:00
vladmandic
952696ab20 more cleanup 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-16 10:58:09 +01:00
vladmandic
0d90d95bf6 lint and safeguard glm 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-16 09:40:48 +01:00
vladmandic
a8b9719e5e add flux2-klein sdnq prequantized 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-16 09:00:30 +01:00
vladmandic
f444679fc1 lint 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-16 08:56:30 +01:00
CalamitousFelicitousness
eaa8dbcd42 fix: correct comments and cleanup model descriptions 
- Fix Klein text encoder comment to specify correct sizes per variant
- Lock TAESD decode logging behind SD_PREVIEW_DEBUG env var
- Fix misleading comment about FLUX.2 128-channel reshape (is fallback)
- Remove VRAM requirements from model descriptions in reference files
 2026-01-16 03:24:39 +00:00
CalamitousFelicitousness
749371364b lint 2026-01-16 03:03:47 +00:00
CalamitousFelicitousness
fe99d3fe5d feat: add FLUX.2 Klein model support 
Add support for FLUX.2 Klein distilled models (4B and 9B variants):

- Add pipeline loader for Flux2KleinPipeline
- Add model detection for 'flux.2' + 'klein' patterns
- Add pipeline mapping in shared_items
- Add shared Qwen3ForCausalLM text encoder handling:
  - 4B variants use Z-Image-Turbo's Qwen3-8B
  - 9B variants use FLUX.2-klein-9B's Qwen3-14B
- Add reference entries for distilled (4B, 9B) and base models
- Update diffusers commit for Flux2KleinPipeline support
 2026-01-16 01:35:20 +00:00
vladmandic
387b3c7c36 split reference.json 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-15 08:23:07 +01:00
CalamitousFelicitousness
de3b2b62eb Update reference.json 2026-01-14 05:20:53 +00:00
CalamitousFelicitousness
1be9ceeea1 add GLM-Image to reference models 2026-01-14 03:45:53 +00:00
vladmandic
e4e863fd6d lint and update diffusers 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-12 12:31:29 +01:00
CalamitousFelicitousness
2b8ecf01e2 docs(i18n): improve prompt enhance hints 
Improve formatting and clarity of prompt enhance tooltips:
- Add spacing with <br><br> for better readability
- Clarify that prefix/suffix bypass LLM rewriting
 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
vladmandic
9261b65beb add Qwen-Image-2512-SDNQ-4bit-dynamic 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-10 08:47:28 +01:00
Oleksandr Liutyi
48faa339c1 Fix tag and update cover for Qwen-Image-2512-SDNQ-uint4-svd-r32 2026-01-06 13:25:32 +00:00
vladmandic
3ec1f604d2 cleanup label 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-06 10:57:45 +01:00
vladmandic
18e141e6e4 add qwen-2512 prequants 
Signed-off-by: vladmandic <mandic00@live.com>
 2026-01-06 08:07:22 +01:00
Oleksandr Liutyi
bc8ee0e99e Add Qwen-Image-2512 model cover. And model itself.. 2025-12-31 15:58:57 +00:00
Oleksandr Liutyi
bc4f92ab47 Chroma covers new filenames and parameters 2025-12-26 15:22:20 +00:00
Oleksandr Liutyi
cd86c9017d Remove Chroma v48 2025-12-26 13:30:35 +00:00
Oleksandr Liutyi
c980975d9b Qwen 2511, layered, Ovis. new cover images 2025-12-26 13:03:03 +00:00
vladmandic
bb13aabe17 add ovis-image 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-26 08:05:25 +01:00
vladmandic
c0141de02d add qwen-image-edit-2511 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-24 09:55:08 +01:00
Oleksandr Liutyi
0b5f0d08c9 Kandinsky 5 T2I cover image 2025-12-23 16:36:24 +00:00
vladmandic
86885c6ab3 add qwen-layered prequantized 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-23 07:05:35 +01:00
vladmandic
2a33d9f1a8 add qwen-image-layered 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-22 21:24:27 +01:00
vladmandic
409ad8d2bd add longcat image and image-edit 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-16 08:58:22 +01:00
Vladimir Mandic
29a3473772 Merge pull request #4458 from awsr/interrogate-icon 
Change "interrogate" icon
 2025-12-10 10:44:31 +01:00
vladmandic
a72b98848c cleanup 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-10 10:17:37 +01:00
awsr
f7e04aa57f Update localization files 2025-12-10 00:33:04 -08:00
vladmandic
3a65d561a7 add google-veo-3.1 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-09 19:14:08 +01:00
vladmandic
acca58f50c add kandinsky5 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-12-09 09:47:22 +01:00
Oleksandr Liutyi
a06aecada3 FLUX.2 Dev Cover(s) and size 2025-12-07 14:25:13 +00:00
CalamitousFelicitousness
9505a674ea docs(i18n): add detailed VLM/CLiP tooltips and improve labels 
Add comprehensive tooltips explaining VLM and CLiP parameters:
- New labels for VLM: Prompt, Task, Prefill, Thinking mode
- New labels for CLiP: min/max length, chunk size, flavors
- Detailed hints for sampling parameters (temperature, top-k, top-p)
- Improved system prompt and sampling method descriptions
- Standardized label capitalization
 2025-12-02 23:06:46 +00:00
Oleksandr Liutyi
b4f8b68e50 Z Image Turbo cover images 2025-11-27 18:53:23 +02:00
Disty0
f7b0bbb6e1 Complete Z-Image support 2025-11-27 17:25:36 +03:00
vladmandic
86a506f549 mark prequant in reference 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-11-26 11:34:57 -05:00
vladmandic
ad6458aa7b add flux2 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-11-26 15:47:17 +00:00
vladmandic
08621445b9 add gemini-3-pro-image 
Signed-off-by: vladmandic <mandic00@live.com>
 2025-11-22 12:12:20 -05:00
Oleksandr Liutyi
31a6caddca Photoroom PRX 1024 cover with metadata 2025-11-15 12:47:19 +02:00
Vladimir Mandic
fea88897c8 add prx 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-11-13 17:10:14 -05:00
Vladimir Mandic
4ffc1b6097 add nano-banana 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-11-13 13:14:55 -05:00
Vladimir Mandic
21b3cfdb3c fix pony url 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-11-06 08:06:25 -05:00
Oleksandr Liutyi
d2cf09af64 New model covers for Quantized Flux, Chroma HD, Tempest. New cover of ChronoEdit 2025-11-05 22:56:53 +02:00