voyager-so/shot-reader-8b
image-text-to-text model by voyager-so
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Watch a shot. Get the 3D scene. Shot Reader reads a video shot and works out how it was made: the camera's height, angle, lens and move, who is in frame, where they stand, how they move, and the set around them. It writes all of that as one JSON shot sheet that a 3D tool or a coding agent can rebuild directly in Blender. It's a fine-tune of Qwen3-VL-8B-Instruct, small enough to run on your own GPU. Built by Voyager. Trained and benchmarked on Voyager Cloud, so you can run it there on an H100 in seconds. ¹ Untrained base model, same prompt, 20 held-out shots. Opus and Gemini were given the same prompt and schema, written specifically for reverse-engineering a shot. Speed and cost are for one H100 with vLLM in FP8; bulk throughput is 0.76 s per shot, about $1.50 per million output tokens. AI can already…
Read the full model card ↗ · Preview checked 2026-11-21T10:03:31.393Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
voyager-so/shot-reader-8b is a image-text-to-text model repository published by voyager-so on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 61
- Cumulative likes
- 33
- Hugging Face trending score
- 31
- Reported safetensors parameters
- 8,767,123,696
- Architecture
- Qwen3VLForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-19T21:18:48.000Z
- Last modified
- 2026-11-19T21:37:33.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3-VL-8B-Instruct
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-21T07:00:33.109Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.