CalamitousFelicitousness
27fa48cc99
feat(vqa): major VQA handler refactor with prefill, thinking, and visualization
...
Comprehensive overhaul of the VQA interrogation system including:
- Prefill text support for guiding VLM responses
- Thinking mode support with tag cleanup/retention
- Dynamic prompt/task selection based on model type
- Bounding box visualization for detection results
- Debug infrastructure (SD_VQA_DEBUG env var)
- New model support: MiMo-VL, Nidum Gemma, Allura Gemma
- Model-specific prompt lists (Florence, Moondream)
2025-12-05 00:00:24 +00:00
Vladimir Mandic
f2835499b1
kanvas bindings
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-11-07 12:21:48 -05:00
Vladimir Mandic
58581896f5
cleanup
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-26 10:01:24 -04:00
CalamitousFelicitousness
33f335a98c
VQA class fix f-statement fix
2025-10-26 06:39:05 +00:00
CalamitousFelicitousness
25607693ca
Merge branch 'dev' into qwen3-vl
2025-10-26 06:16:38 +00:00
CalamitousFelicitousness
80bb331169
Prompt enhance resizing and Qwen VL fix
2025-10-26 06:01:33 +00:00
CalamitousFelicitousness
3fc9efa9ee
Add remaining Qwen3VL models up to 8B
2025-10-26 02:53:34 +00:00
CalamitousFelicitousness
1b80147881
Add Qwen3-VL-4B-Instruct
2025-10-25 22:12:20 +01:00
CalamitousFelicitousness
c5d937b9c4
Fix typo in Qwen2.5 VL 4B to 3B
...
https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct has been wrongly named 4B in Captioning menu.
2025-10-25 20:26:38 +01:00
Vladimir Mandic
3e47f3dd9a
video prompt enhance
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Disty0
81bb2b99ef
update florence promptgen repo ids
2025-10-01 21:43:02 +03:00
Vladimir Mandic
22074f4727
cleanup vqa
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 12:02:55 -04:00
Vladimir Mandic
5d0a3e5e8a
fix microsoft-florence
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 10:58:52 -04:00
Vladimir Mandic
d351fdb98f
add more job state updates and update history tab
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-13 10:54:04 -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
d665ac254e
add apple-fastvlm
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-05 14:25:37 -04:00
Vladimir Mandic
05dd0096c9
set default vqa model
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-04 08:38:29 -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
fa44521ea3
offload-never and offload-always per-module and new highvram profile
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-31 11:40:24 -04:00
Vladimir Mandic
f243c35892
improve traceback display
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-21 19:07:35 -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
c559e26616
add builtin framepack
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-08 15:47:07 -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
e8b5ea3847
major refactor: remove backend original
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-07-05 13:16:46 -04:00
Vladimir Mandic
1b4e1ff0ef
enable quants for vlm-captioning
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-29 11:48:05 -04:00
Vladimir Mandic
78330142ae
add moondream2, sdnq xyzgrid timing info
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-27 09:41:32 -04:00
Vladimir Mandic
5b486a6ef1
sdnq add xyz grid support, improve offloading compatibility
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-25 15:32:37 -04:00
Vladimir Mandic
f0d81ee1e0
cleanup
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-10 08:28:19 -04:00
Vladimir Mandic
6489e4c37d
prompt-enhance api support and img2img support
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-08 15:31:07 -04:00
Vladimir Mandic
d12cfdb537
add vlm prompt enhancer
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-05 12:39:45 -04:00
Disty0
dca11dd806
Add jxl to image extension lists
2025-05-01 16:02:50 +03:00
Vladimir Mandic
d1c3b97c65
add prompt enhance
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-28 14:05:28 -04:00
Vladimir Mandic
8bcc4527ea
add vlm ByteDance/Sa2VA 1b and 4b
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-26 11:10:23 -04:00
Vladimir Mandic
a91c95870d
remote vae encode
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-15 17:03:37 -04:00
Vladimir Mandic
dbfd59434f
add gemma3
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-15 15:30:57 -04:00
Disty0
30afbd036d
Fix circular import between sd_models.py and shared.py
2025-03-11 17:03:33 +03:00
Vladimir Mandic
041f0bbf97
regenerate locales and rerun all translations
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-18 10:32:39 -05:00
Vladimir Mandic
1ee151b533
update diffusers
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-18 08:23:33 -05:00
Vladimir Mandic
b6990151c4
caption tab modernui support
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-17 10:59:22 -05:00
Vladimir Mandic
a4b3dc269e
modernize clip interrogate
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-16 19:37:09 -05:00
Vladimir Mandic
f3dd9b9646
vlm advanced settings and batch processing
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 14:34:28 -05:00
Vladimir Mandic
e95bd93f67
caption ui redesign
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 12:57:19 -05:00
Vladimir Mandic
8906f962ad
deepseek-vl2 experiments
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 10:10:04 -05:00
Vladimir Mandic
abd439d97c
add joycaption
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 10:10:04 -05:00
Vladimir Mandic
1f2fc929f7
add joytag
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-15 10:10:04 -05:00
Vladimir Mandic
640aff898c
global lancosz
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-10 11:24:05 -05:00
Vladimir Mandic
aa1a5650e1
lint
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-04 09:20:30 -05:00
Vladimir Mandic
372b464e3e
improve python 3.12 compatibility
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-04 08:54:41 -05:00
Vladimir Mandic
7831ee10db
remove-background: ben2
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-03 09:08:36 -05:00
Vladimir Mandic
e40b33d237
add vlms: qwen-vl2, smol-vl2, toriigate
...
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-02 17:07:43 -05:00