Spaces:

suplo6669
/

Enhancer

Sleeping

App Files Files Community

Enhancer / tools

Commit History

Sep 14

05:33
research: audit blur routing and specify kernel feasibility gates

supli6669

0b8ac89

Sep 13

14:36
test: evaluate bounded deblur and document quality rejection

supli6669

27c5524
14:13
feat: add isolated regional sharpening experiments and gates

supli6669

4afd216
02:38
fix: sharpen source detail before upscaling

supli6669

922a7cf

Sep 12

14:07
perf: defer UI restoration loading and separate source blend

supli6669

20e323e
02:07
fix: preserve source detail and color during enhancement

supli6669

7a6485d

Sep 9

14:45
feat(p3): complete automated Kaggle GPU 2-iteration verification gate

supli6669

8c41c5b

Sep 8

09:29
feat: package isolated two-step Kaggle GPU verification

supli6669

7f910bb
05:23
feat: simplify dataset review with conservative experiment splits

supli6669

05771b6
03:11
feat: add resumable dataset review and frozen baseline gates

supli6669

26efe9c

Sep 7

15:24
fix: restore pipeline correctness and gate training on verified data

supli6669

f7c0974

Sep 4

13:17
fix(scheduler): patch BasicSR CosineAnnealingRestartLR out-of-bounds crash on resume

supli6669

02920b7
12:56
fix(pipeline): force zero distortion on pure quality, fix radio state sync, and extend training to 6000 iters

supli6669

2371881

Sep 2

16:47
test(pipeline): modernize Phase 7 A/B model and preset verification suite

supli6669

83c9930
16:10
feat(universal): implement universal non-face image restoration, Real-ESRGAN multi-model engine, and compat shim

supli6669

675aba8
15:42
fix(realesrgan): patch torchvision functional_tensor import in basicsr degradations

supli6669

e959c89
14:54
feat(realesrgan): add Kaggle GPU super-resolution training pipeline and runner

supli6669

07c8f01
07:11
feat: v3 ONNX support, ArcFace paths, CPU batch fix, kaggle runner, get_available_models UI

supli6669

258dc9e
06:06
fix(dataset): robust synthetic fallbacks for dataset preparation

supli6669

cf2966a
05:44
feat(v2.9.0): deliver Ultimate Glamour & Aesthetics Suite (crystal skin, glossy lips, doll-eye, golden hour)

supli6669

7fd0530
04:54
fix: ensure basicsr/version.py is tracked and generated properly

supli6669

9908062
04:35
fix: resolve dataset preparation pathing for Kaggle cloud training

supli6669

aee05c0
04:26
feat: trigger automated Kaggle Cloud GPU Stage III training

supli6669

3ad4d0c
04:22
fix: update Kaggle API payload structure and verified live deployment

supli6669

2dd2d60
04:19
feat: add automated Kaggle Cloud GPU training pipeline and runner

supli6669

a27fd75
04:01
feat: deliver Razor-Sharp & Super-Clarity Engine (v2.8.0) with Laplacian multi-scale pyramid clarity, optical deblur, and crystal dehaze

supli6669

c7ef7ad
03:34
feat: deliver Ultimate Studio Pro Suite (v2.7.0) with 400% zoom loupe, anti-glare matte skin, natural makeup palette, and 8K upscale

supli6669

36864d0

Sep 1

19:17
feat: deliver Next-Level Studio AI Features (v2.6.0) with iris catchlight glow, hair strand super-clarity, and 3D studio relighting

supli6669

9a26028
18:33
feat: deliver Studio AI Enhancement Suite (v2.5.0) with interactive split slider, dark circle concealer, cinematic film LUTs, and portrait bokeh

supli6669

f887be0
18:03
fix: comprehensive edge-case hardening, dynamic preset bindings, and model weight size validation

supli6669

42b6da2
17:52
fix: resolve image upload decoding errors, fix EXIF orientation, and add Docker build pre-download weights

supli6669

e08c5be
17:43
feat: add Studio Portrait Beauty Suite with teeth whitening, ocular catchlight sparkle, and auto tone glow balance

supli6669

bf9109c
17:38
feat: add multi-image batch processing, HTML quality report card, live webcam beautifier, and chromatic aberration filter

supli6669

c27ce82
17:34
feat: add video AI restoration, Studio Skin 2.0 bilateral synthesis, and multi-tab benchmark explorer UI

supli6669

44bce3d
17:15
feat: complete end-to-end model benchmark evaluation, colab training notebook, and UI comparison GIF exporter

supli6669

d4c639f

Jul 23

05:57
feat: enforce held-out benchmark workflow

supli6669

0193004
05:51
feat: add model quality workflow gate

supli6669

2d06408

Jul 22

06:10
fix: align test_ab_ui_pipeline.py with single return value of process_image

supli6669

c55060c
06:08
fix: resolve Windows cp1252 terminal encoding in test_all.py with 100% pass rate

supli6669

f2a9898
05:45
feat: add master system verification test suite test_all.py with 100% pass rate and exit code 0

supli6669

f28ecd6
05:43
feat: complete Phase 6 Stage II Transformer fine-tuning setup and verification with exit code 0

supli6669

a706587
05:12
feat: verify Phase 7 A/B Model & Preset Pipeline with exit code 0

supli6669

a83a4d3
05:09
feat: verify Phase 4 Dataset Expansion & Game Character Mixing with exit code 0

supli6669

06017be

Jul 20

14:04
docs: update handover.md and add dynamic fallback verification to quantize_onnx_static.py

supli6669

c4942a1
13:53
fix: remove static quantization from Dockerfile build and add fail-safe ONNX loader

supli6669

15b2edb
12:18
fix(hf): integrate Static INT8 ONNX build into Dockerfile and fix thread state guard in app.py

supli6669

b42379b
11:47
feat: implement static INT8 ONNX quantization tool & UI model engine selector

supli6669

77a7159

Jul 19

12:44
fix: resolve B11 (offline setuptools wheel build via base64 encoding and Dockerfile update) and finalize Task 11 bug fixes

supli6669

a30aa2c

Jul 18

08:03
fix: update download_weights.py to use stable github release urls

supli6669

d635133
07:38
fix: resolve Hugging Face deployment crashes and dependency conflicts

supli6669

93fffe5

Commit History

Sep 14

research: audit blur routing and specify kernel feasibility gates

Sep 13

test: evaluate bounded deblur and document quality rejection

feat: add isolated regional sharpening experiments and gates

fix: sharpen source detail before upscaling

Sep 12

perf: defer UI restoration loading and separate source blend

fix: preserve source detail and color during enhancement

Sep 9

feat(p3): complete automated Kaggle GPU 2-iteration verification gate

Sep 8

feat: package isolated two-step Kaggle GPU verification

feat: simplify dataset review with conservative experiment splits

feat: add resumable dataset review and frozen baseline gates

Sep 7

fix: restore pipeline correctness and gate training on verified data

Sep 4

fix(scheduler): patch BasicSR CosineAnnealingRestartLR out-of-bounds crash on resume

fix(pipeline): force zero distortion on pure quality, fix radio state sync, and extend training to 6000 iters

Sep 2

test(pipeline): modernize Phase 7 A/B model and preset verification suite

feat(universal): implement universal non-face image restoration, Real-ESRGAN multi-model engine, and compat shim

fix(realesrgan): patch torchvision functional_tensor import in basicsr degradations

feat(realesrgan): add Kaggle GPU super-resolution training pipeline and runner

feat: v3 ONNX support, ArcFace paths, CPU batch fix, kaggle runner, get_available_models UI

fix(dataset): robust synthetic fallbacks for dataset preparation

feat(v2.9.0): deliver Ultimate Glamour & Aesthetics Suite (crystal skin, glossy lips, doll-eye, golden hour)

fix: ensure basicsr/version.py is tracked and generated properly

fix: resolve dataset preparation pathing for Kaggle cloud training

feat: trigger automated Kaggle Cloud GPU Stage III training

fix: update Kaggle API payload structure and verified live deployment

feat: add automated Kaggle Cloud GPU training pipeline and runner

feat: deliver Razor-Sharp & Super-Clarity Engine (v2.8.0) with Laplacian multi-scale pyramid clarity, optical deblur, and crystal dehaze

feat: deliver Ultimate Studio Pro Suite (v2.7.0) with 400% zoom loupe, anti-glare matte skin, natural makeup palette, and 8K upscale

Sep 1

feat: deliver Next-Level Studio AI Features (v2.6.0) with iris catchlight glow, hair strand super-clarity, and 3D studio relighting

feat: deliver Studio AI Enhancement Suite (v2.5.0) with interactive split slider, dark circle concealer, cinematic film LUTs, and portrait bokeh

fix: comprehensive edge-case hardening, dynamic preset bindings, and model weight size validation

fix: resolve image upload decoding errors, fix EXIF orientation, and add Docker build pre-download weights

feat: add Studio Portrait Beauty Suite with teeth whitening, ocular catchlight sparkle, and auto tone glow balance

feat: add multi-image batch processing, HTML quality report card, live webcam beautifier, and chromatic aberration filter

feat: add video AI restoration, Studio Skin 2.0 bilateral synthesis, and multi-tab benchmark explorer UI

feat: complete end-to-end model benchmark evaluation, colab training notebook, and UI comparison GIF exporter

Jul 23

feat: enforce held-out benchmark workflow

feat: add model quality workflow gate

Jul 22

fix: align test_ab_ui_pipeline.py with single return value of process_image

fix: resolve Windows cp1252 terminal encoding in test_all.py with 100% pass rate

feat: add master system verification test suite test_all.py with 100% pass rate and exit code 0

feat: complete Phase 6 Stage II Transformer fine-tuning setup and verification with exit code 0

feat: verify Phase 7 A/B Model & Preset Pipeline with exit code 0

feat: verify Phase 4 Dataset Expansion & Game Character Mixing with exit code 0

Jul 20

docs: update handover.md and add dynamic fallback verification to quantize_onnx_static.py

fix: remove static quantization from Dockerfile build and add fail-safe ONNX loader

fix(hf): integrate Static INT8 ONNX build into Dockerfile and fix thread state guard in app.py

feat: implement static INT8 ONNX quantization tool & UI model engine selector

Jul 19

fix: resolve B11 (offline setuptools wheel build via base64 encoding and Dockerfile update) and finalize Task 11 bug fixes

Jul 18

fix: update download_weights.py to use stable github release urls

fix: resolve Hugging Face deployment crashes and dependency conflicts