Upload app.py

Upload app.py

Delete static/

Delete Dockerfile

Upload requirements.txt

Upload README.md

Upload app.py

Update frontend model constants to match HF backend

Upgrade to HF models: Qwen2.5-72B text, Qwen2.5-VL-7B vision, SDXL image. Remove Gemini dependency.

Fix env var loading: use function get_gemini_key() at runtime + add debug endpoints

Update README with Gemini setup instructions

Switch to Gemini + Pollinations AI (free, no HF token needed)

Change SDK to docker

Fix API routing: static files AFTER API routes + CORS

Delete index.html with huggingface_hub

Update frontend with local /api/* endpoints (no CORS)

Update Dockerfile for FastAPI backend

Add requirements.txt

Add FastAPI backend proxy

Remove old static files

Add Dockerfile for backend

Fix critical API issues: 1) Token UI for HF access, 2) Correct VLM chat API format, 3) Separate Txt2Img vs Inpainting models, 4) Better error messages

Fix character detection: correct Qwen-VL API format (OpenAI chat completions) and add JSON sanitization

Update README with inpainting features

Add inpainting paint mask feature with SDXL Inpainting model

Upload index.html with huggingface_hub

initial commit