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, 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

# 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

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.

Citation

@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}
}