Content Generation
MIFY provides a dedicated content generation system at /content-gen with three independent execution paths.
Three Execution Paths
Section titled “Three Execution Paths”| Path | How It Works | Best For |
|---|---|---|
| MIFY Queue | Submits ComfyUI workflows to external GPU providers (Novita, Vast) | High-quality image and video generation |
| AI Provider | Direct calls to AI providers with sync or SSE streaming | Text generation, quick image generation |
| ComfyUI Local | Runs workflows on your local ComfyUI installation | Custom models, local development |
Using Content Generation
Section titled “Using Content Generation”1. Browse Workflows
Section titled “1. Browse Workflows”Navigate to /content-gen to see available generation workflows. Each workflow has a dynamic form based on its parameters — you’ll see different input fields depending on the workflow.
2. Fill in Parameters
Section titled “2. Fill in Parameters”Workflows support 12 input types with 11 UI widgets:
| Widget | Input Type | Example |
|---|---|---|
| Text field | String | Prompt text |
| Textarea | Long text | Detailed descriptions |
| Slider | Number (with range) | Strength, steps, guidance |
| Image upload | Image URL or file | Reference images |
| Select dropdown | Enum/select | Model selection, style choices |
| Checkbox | Boolean | Enable/disable features |
| Model picker | Model reference | Choose a specific AI model |
3. Submit and Track
Section titled “3. Submit and Track”After submitting:
- MIFY Queue: Job is queued for GPU processing. You’ll see status updates as it progresses.
- AI Provider: Response arrives immediately (sync) or streams in real-time (SSE).
- ComfyUI Local: Runs on your local machine, results collected when complete.
4. View Results
Section titled “4. View Results”Visit /content-gen/history to see all your past generations. Click any run to see:
- Generated artifacts (images, videos)
- Input parameters used
- Cost and timing information
- Error details (if failed)
Execution Layer
Section titled “Execution Layer”For image/video generation via the MIFY Queue path, jobs are processed by the execution layer:
- Run types: Image, video, and vision (image analysis)
- Training: Submit model fine-tuning jobs with datasets uploaded to Cloudflare R2
- Model registry: Store and reuse trained model artifacts
Training Workflows
Section titled “Training Workflows”- Navigate to
/training/new - Upload a dataset (images/files)
- Select a training preset
- Submit and monitor progress at
/training/[id]
Trained models become available for use in future generation workflows.