docs: update documentation for image editing feature

- Add /edit endpoint examples and description
- Update model tables with editing capabilities
- Rename BASE_URL to IMAGE_BASE_URL in docs
- Add DEFAULT_MODEL documentation
- Remove "production-ready" marketing language

Author: danielcopper

CONFIGURATION.md

@@ -37,12 +37,19 @@ Complete configuration reference for the Image Generation API.
 - Default: `./generated_images`
 - Docker: Use volume mount (e.g., `/app/generated_images`)
 
-**`BASE_URL`**
+**`IMAGE_BASE_URL`**
 - Public base URL for serving images
 - Default: `http://localhost:8000`
-- Production: Your domain (e.g., `https://api.example.com`)
+- Example: `https://api.example.com`
 - Used to construct full image URLs
 
+### Model Defaults
+
+**`DEFAULT_MODEL`**
+- Default model for generation/editing when not specified in request
+- Example: `gpt-image-1`, `dall-e-3`
+- Optional - if not set, first available model is used
+
 ### Security
 
 **`API_BEARER_TOKEN`**
@@ -76,36 +83,30 @@ Complete configuration reference for the Image Generation API.
 ### OpenAI Models
 
 **dall-e-2**
-- Aspect Ratios: `1:1` only (all others fallback to square)
+- Aspect Ratios: `1:1` only
 - Quality: Not supported
 - Max Images (n): 4
-- Sizes: 1024x1024
+- Editing: Yes (mask-based)
 
 **dall-e-3**
 - Aspect Ratios: `1:1`, `16:9`, `9:16`
 - Quality: `standard`, `hd`
 - Max Images (n): 1
-- Sizes: 1024x1024, 1792x1024, 1024x1792
+- Editing: No
 
 **gpt-image-1**
 - Aspect Ratios: `1:1`, `16:9`, `9:16`
 - Quality: Not supported
 - Max Images (n): 4
-- Sizes: 1024x1024, 1536x1024, 1024x1536
+- Editing: Yes (mask-based)
 
 ### Google Gemini Models
 
 **gemini-2.0-flash-preview-image-generation**
 - Aspect Ratios: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`
 - Quality: Not supported
 - Max Images (n): 4
-- Fast generation
-
-**imagen-3.0-generate-002**
-- Aspect Ratios: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`
-- Quality: Not supported
-- Max Images (n): 4
-- High quality output
+- Editing: Yes (prompt-based)
 
 ## Provider Setup
 
@@ -204,6 +205,35 @@ Constraints:
 - dall-e-3: max 1
 - Others: max 4
 
+## Image Editing
+
+The `/edit` endpoint supports two editing modes:
+
+### Mask-based Editing (OpenAI)
+
+Used with `dall-e-2` and `gpt-image-1`. Requires:
+- `image`: Source image (upload or URL)
+- `mask`: PNG with transparent areas marking regions to edit
+- `prompt`: Description of what to generate in masked area
+
+The mask should have transparent (alpha=0) pixels where editing should occur.
+
+### Prompt-based Editing (Gemini)
+
+Used with `gemini-2.0-flash-preview-image-generation`. Requires:
+- `image`: Source image (upload or URL)
+- `prompt`: Natural language description of the edit
+
+No mask needed - Gemini understands what to change from the prompt alone.
+
+### Input Methods
+
+Images can be provided two ways:
+- **File upload**: `image=@photo.png` (multipart form)
+- **URL reference**: `image_url=http://localhost:8000/images/abc.png`
+
+URL reference works with previously generated images or external URLs.
+
 ## Authentication
 
 ### No Authentication
@@ -245,7 +275,7 @@ volumes:
 For reverse proxy or custom domain:
 
 ```env
-BASE_URL=https://api.yourdomain.com
+IMAGE_BASE_URL=https://api.yourdomain.com
 ```
 
 Images will be served at: `https://api.yourdomain.com/images/filename.png`

README.md

@@ -1,17 +1,15 @@
 # Image Generation OpenAPI Server
 
-Production-ready OpenAPI server for AI image generation with LiteLLM proxy integration (cost tracking) and direct API fallback support for OpenAI DALL-E and Google Gemini models.
+OpenAPI server for AI image generation and editing. Supports LiteLLM proxy (for cost tracking) and direct API access to OpenAI and Google Gemini.
 
 ## Features
 
-- **LiteLLM Integration**: Primary provider with automatic cost tracking and unified API
-- **Multi-Provider Support**: OpenAI (DALL-E 3, GPT-Image-1) + Google Gemini (Imagen 3.0, Flash)
-- **Dynamic Model Discovery**: Auto-loads available models from LiteLLM
-- **SSE Streaming**: Real-time progress updates during generation
-- **Flexible Responses**: JSON, SSE stream, or HTML preview
-- **Local Storage**: Images saved locally and served via static files
-- **Comprehensive API**: Full OpenAPI/Swagger documentation
-- **Production Ready**: Docker support, health checks, authentication
+- **Image Generation**: Create images from text prompts
+- **Image Editing**: Edit existing images with mask-based inpainting (OpenAI) or prompt-based editing (Gemini)
+- **Multi-Provider**: OpenAI (DALL-E 3, GPT-Image-1) and Google Gemini
+- **LiteLLM Integration**: Unified API with cost tracking
+- **Dynamic Models**: Auto-discovers available models from LiteLLM
+- **Multiple Response Formats**: URL, base64, or markdown
 
 ## Quick Start
 
@@ -62,51 +60,48 @@ docker-compose up -d
 
 ## API Examples
 
-### Generate Image (Standard)
+### Generate Image
 
 ```bash
 curl -X POST "http://localhost:8000/generate" \
   -H "Content-Type: application/json" \
   -d '{
-    "prompt": "A serene mountain landscape at sunset",
-    "provider": "litellm",
+    "prompt": "A mountain landscape at sunset",
     "model": "dall-e-3",
-    "aspect_ratio": "16:9",
-    "quality": "hd"
+    "aspect_ratio": "16:9"
   }'
 ```
 
-### Generate with SSE Streaming
+### Edit Image (Mask-based, OpenAI)
 
 ```bash
-curl -N "http://localhost:8000/generate-stream" \
-  -H "Content-Type: application/json" \
-  -d '{
-    "prompt": "A futuristic city skyline",
-    "aspect_ratio": "9:16"
-  }'
+curl -X POST "http://localhost:8000/edit" \
+  -F "image=@photo.png" \
+  -F "mask=@mask.png" \
+  -F "prompt=Replace the sky with a sunset" \
+  -F "provider=openai" \
+  -F "model=gpt-image-1"
 ```
 
-### Python Client
+### Edit Image (Prompt-based, Gemini)
 
-```python
-import requests
+```bash
+curl -X POST "http://localhost:8000/edit" \
+  -F "image=@photo.png" \
+  -F "prompt=Make the background more colorful" \
+  -F "provider=gemini"
+```
 
-response = requests.post(
-    "http://localhost:8000/generate",
-    json={
-        "prompt": "A cute cat wearing sunglasses",
-        "provider": "litellm",  # or "openai", "gemini"
-        "aspect_ratio": "1:1",
-        "n": 1
-    }
-)
+### Edit via URL Reference
 
-result = response.json()
-print(f"Image URL: {result['image_url']}")
+```bash
+curl -X POST "http://localhost:8000/edit" \
+  -F "image_url=http://localhost:8000/images/abc123.png" \
+  -F "prompt=Add a hat to the person" \
+  -F "provider=gemini"
 ```
 
-### List Available Models
+### List Models
 
 ```bash
 curl "http://localhost:8000/models"
@@ -136,16 +131,19 @@ GEMINI_API_KEY=...
 
 ### OpenAI
 
-- **dall-e-3**: HD quality, multiple aspect ratios, n=1 only
-- **gpt-image-1**: Newest model, multiple sizes
-- **dall-e-2**: Square only, fast generation
+| Model | Generation | Editing | Notes |
+|-------|------------|---------|-------|
+| dall-e-3 | Yes | No | HD quality, multiple aspect ratios |
+| gpt-image-1 | Yes | Yes (mask) | Fast, supports inpainting |
+| dall-e-2 | Yes | Yes (mask) | Square only |
 
 ### Google Gemini
 
-- **gemini-2.0-flash-preview-image-generation**: Fast generation
-- **imagen-3.0-generate-002**: High quality
+| Model | Generation | Editing | Notes |
+|-------|------------|---------|-------|
+| gemini-2.0-flash-preview-image-generation | Yes | Yes (prompt) | Fast, prompt-based editing |
 
-See [CONFIGURATION.md](CONFIGURATION.md) for detailed model capabilities.
+See [CONFIGURATION.md](CONFIGURATION.md) for details.
 
 ## Open WebUI Integration
 
@@ -161,20 +159,21 @@ For admin/global tools, configure in Admin Settings with server-accessible URL.
 
 ### Image Generation
 
-- `POST /generate` - Generate image (JSON response)
-- `POST /generate-stream` - Generate with SSE progress
-- `POST /generate-preview` - Generate with HTML preview
+- `POST /generate` - Generate image from prompt
+
+### Image Editing
+
+- `POST /edit` - Edit existing image (supports file upload or URL reference)
 
-### Model Management
+### Models
 
 - `GET /models` - List available models
 - `POST /models/refresh` - Refresh model list from LiteLLM
 
-### Health & Info
+### Info
 
 - `GET /health` - Health check + provider status
-- `GET /` - API information
-- `GET /docs` - Interactive API documentation
+- `GET /docs` - API documentation
 
 ## Configuration
 
@@ -200,36 +199,19 @@ With coverage:
 pytest --cov=app --cov-report=html
 ```
 
-## Development
+## Project Structure
 
-Project structure:
-
-```txt
+```
 app/
-├── main.py              # FastAPI application
-├── core/                # Configuration & utilities
-├── api/routes/          # API endpoints
-├── schemas/             # Pydantic models
-├── services/            # Business logic
-└── utils/               # Helpers
-
-tests/                   # Test suite
+├── main.py              # FastAPI app
+├── core/                # Config, security
+├── api/routes/          # Endpoints (generate, edit, models, health)
+├── schemas/             # Request/response models
+└── services/            # Provider integrations
+
+tests/                   # Tests
 ```
 
 ## License
 
 MIT
-
-## Contributing
-
-Contributions welcome! Please ensure:
-
-- Tests pass (`pytest`)
-- Code follows project style
-- Documentation updated
-
-## Support
-
-- Issues: GitHub Issues
-- Docs: `/docs` endpoint
-- Health: `/health` endpoint