---
license: mit
language:
  - en
tags:
  - video-generation
  - text-classification
  - routing
  - steady
  - byteSteady
  - switchboard
library_name: steady
---

# switchboard-video-v1

8-classifier pipeline for video generation prompt routing. Each model classifies
one dimension of a video generation request: length, complexity, style, quality,
camera movement, physics, reference modality, and cost tier.

## Architecture

These models power [switchboard](https://github.com/xDarkicex/switchboard), a
zero-alloc AI proxy engine that classifies incoming prompts and routes them to
the cheapest capable video generation provider.

```
POST /v1/chat/completions
  → extract user message
  → 8-classifier pipeline (~2ms)
  → logic-based routing rules
  → upstream provider (runway, openai, kling, stability)
```

## Models

| Model | Dimension | Labels | Size |
|---|---|---|---|
| `length.bin` | Duration | short, medium, long, multi_stage | 51 MB |
| `complexity.bin` | Scene complexity | simple, multi_subject, multi_stage | 51 MB |
| `style.bin` | Visual style | photorealistic, cinematic, animation, 3d, motion_graphics | 51 MB |
| `quality.bin` | Resolution / fidelity | basic, 4k, 8k, production-grade | 51 MB |
| `camera.bin` | Camera movement | static, dolly, tracking, orbital, fpv | 51 MB |
| `physics.bin` | Physical simulation | none, basic, particle, fluid, cloth | 51 MB |
| `refs.bin` | Reference modality | none, image, video, audio, multi | 51 MB |
| `cost.bin` | Cost tier | cheap, medium, expensive | 51 MB |

## Training

```sh
# Clone the switchboard repo
git clone https://github.com/xDarkicex/switchboard
cd switchboard

# Generate training data
./switchboard synth \
  --preset ./presets/video/synth.yaml \
  --real ./presets/video/real_prompts.yaml \
  --per-intent 1500 --output ./presets/video/training.txt

# Train all 8 models
go run ./scripts/train-pipeline
```

Training data: 42,731 examples (231 human-annotated + 5,000 auto-tagged + 37,500 synthetic).
42,731 examples × 8 labels = 341,848 multi-label training lines.

## Inference

```go
import "github.com/xDarkicex/switchboard/internal/operator"

cfg := operator.PipelineConfig{
    Style: operator.PipelineSlot{
        ModelPath: "models/style.bin",
        DefaultVal: "cinematic",
        Labels: []string{"cinematic", "photorealistic", "animation", "3d", "motion_graphics"},
    },
    // ... 7 more dimensions
}
pipeline, _ := operator.NewPipeline(cfg)
defer pipeline.Close()

tags, _ := pipeline.Classify("Make a cinematic video of a dragon")
// tags.Style = "cinematic"
// tags.Length = "medium"
// tags.Cost = "medium"
```

## License

MIT — same as [switchboard](https://github.com/xDarkicex/switchboard).

## Citation

```bibtex
@software{switchboard2026,
  author = {xDarkicex},
  title = {switchboard-video-v1: 8-classifier pipeline for video generation routing},
  year = {2026},
  url = {https://huggingface.co/LibraVDB/switchboard-video-v1}
}
```