Shot Reader 8B
It looks at a video frame and works out how it was shot: the camera height, angle, lens and movement, who is in frame, where they stand, how they move and what the surroundings are. It writes everything as one JSON description of the shot, from which a 3D program or a coding agent can build the scene right in Blender. It is a fine-tune of Qwen3-VL-8B-Instruct. It suits storyboards, analysing other people's videos and recreating scenes.
- Developer
- Voyager, not stated
- First release
- Nov 2026
- Latest release
- Nov 2026
- Sizes
- 8B
- License
- Commercial use allowedApache 2.0 (a fine-tune of Qwen3-VL-8B-Instruct)
- Russian
- Not stated
- Running
- On your own serverNeeds a GPU
- Industries
- Media and production, Marketing and content
What it does
- analysing other people's shots to recreate them in Blender
- describing the camera and staging for a storyboard
- preparing data for 3D scenes from video
Where it is used
Hardware requirements
Versions
- Shot Reader 8B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can Shot Reader 8B be used in a commercial project?
Yes. License: Apache 2.0 (a fine-tune of Qwen3-VL-8B-Instruct). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Shot Reader 8B need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Shot Reader 8B support Russian?
The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.
Where can I download Shot Reader 8B and what does it cost?
The Shot Reader 8B weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.
DetailsImage + textWeVisOne-VLWeChat Vision, Tencent · ChinaCommercial use allowedA unified vision model from WeChat Vision (Tencent) based on Qwen3-VL: one model does both object search and precise perception. It finds objects by description, points to the needed item, counts items, marks points, reads text, and at the pixel level cuts out an object by description and makes an alpha matte on request, for which a small 9.6M-parameter decoder was added to the model. Two sizes, 2B and 4B. It suits image labeling, cutting products out of a background and counting items in a photo. Prompt languages are not stated on the card.
DetailsImage + textMiniCPM-VOpenBMB (ModelBest and Tsinghua University) · ChinaCommercial use allowedCompact vision models that run even on a phone or laptop. Good at reading text in photos and understanding video; version 4.6 is only 1.3B. The fresh 4.7 comes in two sizes, 1B and 35B-A3B, the first MoE model in the family. According to the authors, 35B-A3B runs on an iPhone 17 Pro Max at 13+ tokens per second with 3 GB of memory thanks to their way of loading experts. The figures come from the authors themselves.
DetailsSource: huggingface.co/voyager-so/shot-reader-8b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


