Configuration

After installation, you need to configure services to use Pixelle-Video.

---

LLM Configuration

LLM (Large Language Model) is used to generate video scripts.

Quick Preset Selection

1. Select a preset model from the dropdown:
2. Qianwen (recommended, great value)
3. GPT-4o
4. DeepSeek

5. Ollama (local, completely free)

6. The system will auto-fill base_url and model

7. Click「🔑 Get API Key」to register and obtain credentials

8. Enter your API Key

---

Image/Video Generation Configuration

Two options available:

Local Deployment

Using local ComfyUI service:

1. Install and start ComfyUI
2. Enter ComfyUI URL (default http://127.0.0.1:8188)
3. Click "Test Connection" to verify
4. (Optional) Enter ComfyUI API Key (get from Comfy Platform)

Cloud Deployment (Recommended)

Using RunningHub cloud service, no local GPU required:

1. Register for a RunningHub account
2. Obtain API Key
3. Enter API Key in configuration
4. Configure advanced options (optional):
5. Concurrent Limit: Set number of simultaneous tasks (1-10, default 1 for regular members)
6. Instance Type: Choose 24GB or 48GB VRAM machine (48GB for large video generation)

---

Save Configuration

After filling in all required configuration, click the "Save Configuration" button.

Configuration will be saved to config.yaml file.

---

Next Steps

• Quick Start - Create your first video