Creative Methods
From Script to Production Canvas: Complete AI Drama Storyboard & Multi-Model Workflow
Stop switching between 10 browser tabs. Organize characters, shots, keyframing, and multi-model video generation on a single infinite canvas.
On this page
What should you prepare first?
Write a few sentences about the story’s goal, the relationships between characters and what changes. Break the story into shots you can review individually. For each shot, record the characters, setting, action and visual focus.
Prepare character references and scene assets you have permission to use. Organizing the inputs gives you a basis for judging what meets the goal and what needs revision.
How do you organize shots on a canvas?
Add text and reference assets to the canvas, then connect them to the relevant generation nodes. Complete one shot first, checking the model, inputs and output before expanding to more shots.
Keep different versions and unsuccessful results. Change one main condition at a time so you can compare the effect. Review character appearance, clothing, eyelines and scene continuity shot by shot.
What needs checking after generation?
Confirm the shots you will use, their aspect ratios and the delivery requirements. A successfully generated clip is not a finished short film. Transitions, editing, sound and subtitles still need to meet the project requirements.
Check the creation interface for model parameters, credits and failure handling. This guide explains an organizational method; it does not report a test of a particular model or guarantee character consistency.
Connect your own API channels and third-party relays
In model-channel settings, enter the Base URL and API key, then configure the protocol, model IDs and required headers from your provider's documentation. Check the image and video modes you need before generating. Paths, resolutions and first/last-frame inputs depend on the connected channel. An adaptation request for an unsupported channel is not a compatibility guarantee.
BYOK supports a custom API endpoint, model key and headers. For OneAPI, NewAPI or another relay, select the OpenAI, Gemini or Claude protocol that matches its actual API, then check model IDs and image/video endpoint support. Not every relay or private protocol works automatically. BYOK model calls have no platform model markup or platform generation-credit deduction; workspace access and provider usage are still billed separately.
Connect only trusted providers and use HTTPS in production. Custom requests are forwarded through the authenticated backend; required prompts, reference assets and credentials take part in the request. Never put API keys, passwords or secret-bearing headers in public canvases, screenshots or support requests.
Frequently asked questions
Do I need to generate every shot at once?
You can first validate the character and visual direction in one shot, then organize the remaining shots step by step.
Can character consistency be guaranteed?
No. You still need to inspect and adjust the results across shots.
How do I transfer a successful character appearance seamlessly from Shot 1 to Shot 2?
Drag the output connection from Shot 1's Last Frame directly into Shot 2's First Frame slot, or set it as a global character reference node to maintain visual continuity across shots.
Can I connect OneAPI, NewAPI and custom headers?
BYOK supports a custom API endpoint, model key and headers. For OneAPI, NewAPI or another relay, select the OpenAI, Gemini or Claude protocol that matches its actual API, then check model IDs and image/video endpoint support. Not every relay or private protocol works automatically. BYOK model calls have no platform model markup or platform generation-credit deduction; workspace access and provider usage are still billed separately.