Fri, 03 Jul 2026 00:43 - Use mounted model cache bucket

Fri, 03 Jul 2026 00:30 - Use YOLO SAM detail masks

Fri, 03 Jul 2026 00:16 - Add Qwen face hair detailer

Thu, 02 Jul 2026 19:47 - Optimize Qwen enhancement stage

Merge branch 'main' of https://huggingface.co/spaces/clopeux/Pro-Realism-Edit-Studio

Refactor requirements: consolidate dependencies into requirements.txt and remove requirements_enhanced.txt

Merge branch 'main' of https://huggingface.co/spaces/clopeux/Pro-Realism-Edit-Studio

Update README and app.py for version 1.0.0: refine descriptions, enhance clarity, and remove redundant code

improved enhancements, created a new app.py with new models

Enhanced Real-ESRGAN GFPGAN detailer

Enhanced Real-ESRGAN GFPGAN detailer

Enhanced: Real-ESRGAN upscaler, GFPGAN face restoration, multi-stage detailer

Enhanced: Real-ESRGAN upscaler, GFPGAN face restoration, multi-stage detailer

Enhanced: Real-ESRGAN upscaler, GFPGAN face restoration, multi-stage detailer

Sun, 28 Jun 2026 04:18 - Add enhance stage

Sun, 28 Jun 2026 00:14 - Convert Phr00t v23 transformer keys

Sat, 27 Jun 2026 23:29 - Fix Phr00t v23 startup loader

Sat, 27 Jun 2026 23:22 - Use Phr00t v23 official source

Update requirements.txt

Remove temporary dimension-flow debug prints

Derive output aspect ratio from first image, not last

Add temporary debug prints for dimension flow (will revert)

Revert "Preserve input image aspect ratio when sliders are at default"

Preserve input image aspect ratio when sliders are at default

Expose a second image input slot in the UI

Add debug diagnostic dashboard

Lower @spaces.GPU duration from 300s to 60s

Replace external vllm-flash-attn3 kernel with PyTorch cuDNN FA3 backend

Disable AOTI compile to dodge spaces==0.49.3 NVML regression

Pin spaces==0.50.0 to dodge today's regression

Bisect AOTI compile duration upward: 600 → 1000

Lower AOTI compile duration 1200 → 600 (cap probe)

Lower AOTI compile duration 1500 → 1200 (cap probe)

Clean up for public release

Add .claude/ to gitignore

Add backup file patterns to gitignore

Fix device mismatch during AOT compilation warmup

Upgrade to Qwen-Image-Edit-2511 with Phr00t v18 transformer

Reduce memory during AOT compilation by offloading text encoder

Revert "Fix OOM by deferring model loading and AOT compilation to runtime"

Fix model link in UI description

Fix OOM by deferring model loading and AOT compilation to runtime

Add *.log to gitignore

routine commit

Agent guidelines

Add custom folder to gitignore for local development

Remove demo files and fix image serving for proper download support

Update app.py

Update app.py

Update app.py