docs: add Open WebUI integration documentation

- Add OPENWEBUI_API_URL and OPENWEBUI_API_KEY to .env.example
- Document Open WebUI integration in CONFIGURATION.md
- Add feature to README.md

Author: danielcopper

.env.example

@@ -53,6 +53,18 @@ FILTER_IMAGE_MODELS=true
 # Cache TTL for model list in seconds (default: 3600 = 1 hour)
 MODEL_CACHE_TTL=3600
 
+# -----------------------------------------------------------------------------
+# Open WebUI Integration (Optional)
+# -----------------------------------------------------------------------------
+# When configured, images are uploaded to Open WebUI's file storage.
+# This ensures images are accessible from anywhere (internal/external).
+
+# Open WebUI instance URL (e.g., https://chat.mydomain.com)
+OPENWEBUI_API_URL=
+
+# API key from Open WebUI (Settings > Account > API Keys)
+OPENWEBUI_API_KEY=
+
 # -----------------------------------------------------------------------------
 # Server Configuration
 # -----------------------------------------------------------------------------

CONFIGURATION.md

@@ -50,6 +50,20 @@ Complete configuration reference for the Image Generation API.
 - Example: `gpt-image-1`, `dall-e-3`
 - Optional - if not set, first available model is used
 
+### Open WebUI Integration
+
+**`OPENWEBUI_API_URL`**
+- Open WebUI instance URL
+- Example: `https://chat.mydomain.com`
+- When set (with API key), images are uploaded to Open WebUI's file storage
+
+**`OPENWEBUI_API_KEY`**
+- API key from Open WebUI
+- Get from: Open WebUI Settings > Account > API Keys
+- Required together with `OPENWEBUI_API_URL`
+
+When both are configured, images are automatically uploaded to Open WebUI. This ensures images work from anywhere - no more URL accessibility issues with Docker or external access.
+
 ### Security
 
 **`API_BEARER_TOKEN`**

README.md

@@ -8,8 +8,8 @@ OpenAPI server for AI image generation and editing. Supports LiteLLM proxy (for
 - **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
+- **Open WebUI Integration**: Auto-upload images to Open WebUI's file storage
 - **Dynamic Models**: Auto-discovers available models from LiteLLM
-- **Multiple Response Formats**: URL, base64, or markdown
 
 ## Quick Start