Story2Board / Engineering
Film Knowledge Base
Story2Board uses a searchable film-reference index to retrieve candidate shot records at request time. The index is not used to train or fine-tune Story2Board's generation-model weights. During indexing, selected frames are analyzed by vision-language services to generate searchable metadata. During generation, a user-selected reference may be sent to the selected model provider for that request. The agent presents candidate matches and explains why they may fit; users decide whether to use them. The service does not provide bulk access, original film files, or dataset export.
This is the data description behind Story2Board's film-reference work: what we describe, how references are used and where coverage stops. It is not a public dataset download or a public search interface.
Database snapshot: . Counts reported by the Story2Board team, not an independent audit.
- Annotated shots
- 275,346
- Films
- 236
- Director style profiles
- 79
- Fields per shot record
- 48
Database size: 8.7 GB. The 48 stored fields are not 48 separate cinematic judgments: the record also needs identifiers and retrieval data. The field guide below describes 27 annotation and text fields in six groups.
What a shot record describes
These are model-generated descriptions and estimates, not ground truth from a camera report. A field existing in the schema does not mean every shot has a usable value for it. Subtitle availability, for example, is separate from description coverage.
Shot language
shot_size- How much of the subject is in frame, from a wide shot to a close-up.
camera_angle- The viewing angle relative to the subject, such as high, low or eye level.
composition- How the subjects and space are arranged inside the frame.
lighting- The apparent lighting pattern, direction and contrast.
color_palette- The dominant colors visible in the image.
color_scheme- The relationship between those colors, such as complementary or monochromatic.
depth_of_field- How much of the scene appears in focus.
focal_length_mm- An estimated focal length in millimeters, not verified camera metadata.
lens_type- The apparent lens category, inferred from the image.
aspect_ratio- The relationship between the frame width and height.
Camera motion
camera_motion- The estimated movement of the camera during the shot.
camera_motion_confidence- The motion analysis confidence score, not a human quality rating.
Scene
interior_exterior- Whether the action appears to take place indoors or outdoors.
setting- The kind of location shown, such as a room, street or landscape.
time_of_day- The apparent time of day in the scene.
weather- Visible weather conditions when they can be inferred.
Subject
subjects- The people, objects or other subjects described in the frame.
subject_count- The annotated number of visible subjects.
subject_position- Where the subjects sit within the frame.
action- What the subjects appear to be doing.
Narrative
emotional_tone- The inferred mood of the shot, rather than a measured audience response.
narrative_purpose- The inferred storytelling role of the shot in context.
Text
description- A natural-language account of what is visible in the shot.
description_zh- A Chinese-language shot description.
context_prefix- Additional scene context attached to the shot description for retrieval.
subtitle_en- English dialogue aligned to the shot, when available.
subtitle_zh- Chinese dialogue aligned to the shot, when available.
Film references in the product
Story2Board maintains a searchable, annotated film-reference index for visual research and shot planning. At request time, the agent retrieves a small number of candidate shot records and explains why they may fit. The service does not provide original film files, bulk access, or dataset export.
Within Story2Board, users can select reference frames as inputs for storyboard image generation. Not every generated panel uses a film reference.
Coverage is not the same as accuracy
These counts measure whether an asset or value is present in a shot record. They do not measure annotation correctness or whether a search result helps a director.
- Keyframes
- 275,346 / 275,346100%
- Image embeddings
- 275,346 / 275,346100%
- Chinese descriptions
- 275,346 / 275,346100%
- Text embeddings
- 117,276 / 275,34642.6%
Known limitations
- One annotation model; no human review. The visual annotations come from a single VLM,
qwen3-vl-flash. They have not been human-reviewed, and we do not report an inter-annotator agreement metric. An inferred mood, lens or narrative role can be wrong. - Text embeddings cover only 42.6%. There are 117,276 text embeddings for 275,346 shot records. Do not read the corpus size as the number of shots available to every text-based search.
- The film list is private. We publish the aggregate film count, not individual titles. This snapshot does not include a verified decade or region breakdown, so it cannot establish how representative the collection is.
A specific comparison with MovieNet
MovieNet is a movie-understanding research dataset from CUHK, published at ECCV 2020. Its official project site reports 1,100 movies and 60,000 trailers. Its paper, table 4(a), reports 46,857 shots from 7,858 trailers in the cinematic-style benchmark. That subset, not MovieNet as a whole, is the relevant comparison here.
| Scope | MovieNet (2020) | Story2Board (2026-09-16) |
|---|---|---|
| Films / trailers | 1,100 films; 60,000 trailers | 236 films |
| Cinematic annotations | 46,857 shots from 7,858 trailers, labeled for scale and movement | 275,346 automatically annotated shot records |
| Fields discussed here | 2 cinematic-style categories: shot scale and movement | 27 annotation and text fields across 6 groups; per-field completeness varies |
| Annotation process | Manual annotations reported in the paper | Automated; no human review or agreement metric |
MovieNet also includes character, scene, action and other annotations. Its two cinematic-style categories are not its entire schema. Our broader record format is designed for storyboard reference retrieval; counting fields does not demonstrate better labels, better retrieval, or a larger movie dataset.
Access and use
In authenticated product workflows, the agent may display a small number of selected reference frames in response to a user's shot-search request. The service does not provide bulk access, original film files, or a dataset export. A user-selected reference may be sent to the selected generation provider only when that workflow is invoked; provider handling is governed by the applicable provider terms and our privacy disclosures. Publishing this description does not grant a license to those materials.
To report a copyright or other rights concern about a film reference, use Feedback in the Story2Board web app or email support@story2board.com. Include your contact details, the work and rights concerned, the specific reference, page, or project, the basis for your request, and a statement confirming the accuracy of the information you provide.
For the product workflow, see the AI storyboard generator. Our references and open-source dependencies are documented separately. Questions about the methodology can go through our contact page.