owntentowntentCreator-owned AI studio
DocsBlogUpdatesPricingLog in
Contents
User Manual
Foundations · automation
Explore · Main
How it works
Pricing
Account
Settings
ComfyUIBring your own GPU (0 credits)
Projects
Production
Autopilot
Control
Storyboard expands each scene as an accordion, managing every shot as a thumbnail + detail alongside the scene summary, characters, and dialogue. Each shot shows its keyframe or generated clip (hover preview + a versions modal when present), with reorder (up/down + drag), edit, and generate buttons. In edit mode you set cinematography fields — shot size, angle, lens, lighting, camera motion, transitions — via selectors, and can apply an auto cinematography suggestion derived from the scene's emotional arc and beat.
Canvas
Blocking (3D)Advanced
Voice & BGMAdvanced
ToolsAdvanced
Story
AI Threads
Develop
Import ScriptAdvanced
Ontology PacksAdvanced
World
Dialogue
Webtoon
ReadAdvanced
FactionsAdvanced
ChaptersAdvanced
OntologyAdvanced
GraphAdvanced
StateAdvanced
ForeshadowingAdvanced
Graph QueryAdvanced
Screenplay AnalysisAdvanced
EvaluateAdvanced
Skill optimizerAdvanced
PlayAdvanced
Output
Shot review
Storyboard
Assets
PosterAdvanced
Music video
Manage
Usage
Project settings
ComfyUI StudioAdvanced
ReportsAdvanced
MemoryAdvanced
KanbanAdvanced
ScheduleAdvanced
Creator & Fanbase
Creator dashboard
Creator page (/c)
Fan community
Release calendar & scheduling
AI fan-service cut
Tools
Language of the Lens
Camera Movements
Shot sizes
Reference analyzer
Back to feature list

Evaluate

Advanced

Location: /studio/[project]/evaluate

Screenshot coming soon
Overview

The Evaluate tab scores your scenario 0-100 against a '4 hormones (dopamine, serotonin, oxytocin, endorphin) + narrative grammar' rubric via a BYOK judge. It shows the overall score, summary, per-axis scores with rationale, suggestions, and top fixes; you can save evaluation versions and compare them on a score-trend sparkline, and refine mode loops evaluate-then-rewrite 1-5 times. It also shows a deterministic (LLM-free) Structure Quality card (slideshow-risk, scene variation, delivery-promise check) and a slop-gate banner for shot review status.

How to use
  1. 1Open the Evaluate tab; the deterministic Structure Quality card and slop gate show first (no key needed).
  2. 2Check the provider (BYOK key or CLI agent) and press Evaluate to get a score.
  3. 3Review per-axis scores, rationale, suggestions, and top fixes.
  4. 4Use Save version to persist a result and compare across versions on the trend.
  5. 5Use Refine with an iteration count to auto-loop evaluate-then-rewrite.
Models used

LLM evaluation goes through the /api/owntent/evaluate proxy: CLI agent (Codex/Claude Code) preferred, or BYOK key. BYOK default models are OpenAI gpt-4o, Anthropic claude-3-7-sonnet-latest, Google gemini-2.0-flash. Structure Quality and the slop gate are LLM-free.

Tip

Even without a key the Structure Quality card and slop gate appear instantly; LLM scoring separately needs a BYOK key or CLI agent. In short-drama format the rubric weights immediate hook and retention more heavily.

PreviousScreenplay AnalysisNextSkill optimizer
owntentowntentCreator-owned AI studio

Make it with AI. Own your fans. A creator-owned short-drama & webtoon studio.

Use cases

  • How it works
  • Script to film
  • Webtoon to film
  • Compare services

Product

  • Pricing
  • Account

Resources

  • Changelog
  • Privacy
  • Terms
  • Acceptable use
  • Copyright
© 2026 owntent, All Rights ReservedSupport: support@owntent.com

owntent's AI features are powered by third-party AI models (such as Seedance, Kling, and GPT-Image). owntent is an independent product, not affiliated with or endorsed by these model providers; model names are trademarks of their respective owners. Generation results vary with model capability.