Back to illustrated tutorials

Canvas and nodes

Features: canvas, text, image, video and audio nodes

A Seagames canvas brings your brief, references and results together. Use text, image, video and audio nodes to build your creative workflow.

Organize inputs before making outputs. Nodes hold content; reference connections describe how they work together.

Start with a signed-in account and a small brief. Make one prop before expanding the project.


What is the canvas?

Pan, zoom and arrange nodes freely. Keep briefs, references and results distinct so versions are easy to compare.

  • Create nodes: add text, images, video and sound, plus dedicated tasks such as 3D.

  • Edit and reference: change content and placement, then verify downstream references.

Text, image, video and audio nodes in the canvas

Create a canvas

Go to Projects and create or open a project. Use a recognizable name such as “Forest Lantern Study”.


Manage projects

Use Projects to reopen and organize work. Check the canvas save state before switching.

  • Use the site’s Projects entry to find existing work.

  • Choose a project from the list to continue with its assets.


Four workspace areas

Explore project actions, creation tools, account information and viewport navigation. Follow the current interface for exact placement.

Project controls

Check the project name and save state. Name projects and key nodes instead of relying only on thumbnails.

  • Confirm saving has finished before switching.

project name and project menu

Canvas creation tools

Double-click an empty area for the creation menu, including upload, the toolbox and style library.

Task types and Upload in the Add node menu
  • Add: create the appropriate task node.

  • Upload: choose local images, video or audio.

  • Toolbox and style library: explore available tools and styles.

  • Generation history: reuse earlier generated assets.

Account controls

Use account and credit controls to review your account. Current pages and pre-submission quotes determine balance, costs and entitlements.

credit and account controls at the top right
  • Review content and references before sharing.

  • Check the balance and each task quote separately.

Minimap and viewport navigation

Use viewport, zoom and minimap controls to navigate larger layouts. Zoom changes your view, not the source resolution.

  • Use viewport navigation to inspect the layout and move to the intended area.

  • Use zoom controls to change viewing distance without changing source pixels.

minimap node layout and zoom controls

Meet the four basic node types

Text nodes 📝

Text nodes hold briefs, prompts, scripts and notes. Put fixed character traits in the body for review and reuse.

manually written sign brief and text editing toolbar

Add text content

Write manually or use AI

Both paths produce a body. AI instructions are separate from generated content.

Manual writing

  • Create Text, choose Write your own content, then type or paste the body.

    manually written sign brief and text editing toolbar

AI writing

  • Enter script requirements, choose an available model, check the quote and generate. Review the body before referencing it downstream.

    AI text instructions, model and quote composer
    AI-generated text body for the sign brief

Example: Write three visual notes for a Forest Shop sign, defining the mushroom roof, blank arrow board and lantern through visible forms and materials.


Image nodes 🎨

Image nodes hold references, characters, scenes and results. Select one to edit, reference or collect the asset.

image node and toolbar after uploading the original sign

Add image content

Upload or generate images

Upload an existing asset, or start a new design with a description and useful references.

  • Upload: choose Upload in the creation menu or drop a supported local file.

    image node and toolbar after uploading the original sign

Image model generation

  • Enter a description, add supported references, then choose model, ratio and resolution.

  • Create a character, prop or scene, beginning with one subject.

  • Check the quote and generate, then inspect silhouette, structure and extra objects.

    image task with a sign reference and leaf-canopy instructions
    Seagames leaf-canopy sign result generated from the reference

Video nodes 🎥

Video nodes hold motion references and generated clips. Watch the whole clip to inspect movement, characters and boundaries.

video node and playback/editing controls after upload

Add video content

Upload or generate video

Manual upload

  • Choose a supported video and wait for the resource to become ready.

    video node and playback/editing controls after upload

Video model generation

  • Create Video and choose an available model that accepts the intended references.

  • Add references and action instructions, review settings and quote, then preview the node’s output.

    video task with an image reference, motion instructions and settings
    generated video result using the leaf-canopy sign reference
  • Choose a supported approach:

    • Generate video from text.

    • Combine image references with action instructions.

    • Use First & last frames.

    • Use media types accepted by Omni reference.

    Watch the subtle leaf and lantern movement, and check that the subject stays stable during the push-in.

Audio nodes 🎵

Music, effects and speech become sound assets. Name them for their destination and listen to their content and decay.

audio playback and trim controls after uploading music

Add audio content

Upload or generate sound

Manual upload

  • Choose an audio file and listen once it is ready.

    audio playback and trim controls after uploading music

Audio model generation

  • Music, effects and speech use separate nodes. Choose the task before entering a description or spoken text.

  • Review settings and quote, then generate and listen for clarity and decay.

    speech task with the Forest Shop greeting text
    generated Forest Shop greeting and playback controls

Review structure in images, continuity in video and listen to sound. A completed task still needs a quality review.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Workflows

Features: workflows, groups, assets and reference connections

Connected nodes make each task’s inputs and outputs visible. Start with a reference-to-image-to-video workflow, then add processing steps as needed.


What is a workflow?

Connect tasks in dependency order

Reference connections pass upstream assets to downstream tasks. Connections do not start paid generation: review references before generating a node or running a ready group.

Basic workflow showcase

For example, upload a mushroom-roof sign, generate a leaf-canopy version from it, then animate the result. Connect the references and group related nodes so you can replace inputs, inspect outputs and reuse the workflow.

Reference and leaf-canopy result connected in a reusable group with Run group available
generated video node and playback controls for the leaf-canopy sign

How to build the workflow

From a reference image to video

1. Upload a style reference

Upload a reference you may use. Create an image node and add it through the reference list or a connection, then verify the input.

Original mushroom-roof sign reference uploaded to the canvas

2. Add a character or prop brief

Create a Text node and choose Write your own content to describe the character or prop. Review any AI-written text before using it. Short briefs can go directly in the image prompt; text references use the body, not the AI request field.

text node containing the Forest Shop sign brief

3. Generate the image

Describe what to make and how to use the reference. Choose a model, ratio and supported settings, then review the quote.

Example: Use the uploaded Forest Shop sign and replace only the mushroom roof with three overlapping green leaves. Keep the blank wooden arrow, right-hand lantern, trunk, mossy base and pale beige background. Add no lettering or new objects.

A short brief can go directly in the image node. Keep the previous output and description; change one dimension per round.

image task using the mushroom sign and leaf-canopy edit instructions
source reference, leaf-canopy result, reference thumbnail, prompt and settings

4. Generate the video

Create a video node separately and add the chosen image. An image’s Reference action creates another image node. Describe subject and camera movement, then review settings and quote.

video task with the leaf-canopy reference, motion description and ten-second settings
generated video node and playback controls for the leaf-canopy sign

Operate on a workflow

Organize connected nodes

Make individual tasks work first, then group them for clear organization and movement.

Group nodes

  • Hold Shift to select the intended nodes, then use Group in the selection toolbar.

  • Use Run group when a group contains a workflow; tasks run in dependency order.

  • Resolve cycles, incomplete inputs or unavailable quotes before running.

Group, Align and Arrange toolbar after Shift-selecting two image nodes
group frame, layout controls and Ungroup action

Keep a reusable workflow

  • Retain the brief, references, settings and approved outputs for the next session.

  • After replacing inputs, inspect downstream reference lists and current model support.

Reference and leaf-canopy result connected in a reusable group with Run group available

Asset management

Keep assets worth reusing

Separate approved assets from experiments and retain their origins. Generation records help reuse settings; uploads do not necessarily carry those records.

Find and reuse assets

  • Choose Add to assets on an available media node and select a folder.

  • Open Assets from the top bar, choose a category, hover an asset and click Use to add it to the canvas.

  • Verify source content before reusing a preview as a reference.

Add to assets action and save-location picker for the completed video
Saved leaf-canopy video in the asset library with Use visible on hover

References in prompts

Make the intended reference explicit

Add existing assets to the generation input and use @ tags to identify the referenced items. Check that each tag points to the intended image or video.

canvas reference-picking mode and the leaf-canopy image to select

How to use references

  • Click Add reference on the destination and select an asset on the canvas, or use a reference connection. Do not add the same asset twice.

  • Specify the shape, palette or motion to preserve and choose the intended reference.

Before submission, verify reference identity, readiness and support by the selected model.

  • Hover over a reference thumbnail and click @ to insert its tag, then describe what to preserve or change.

  • When replacing an asset, remove the unwanted reference and check the new target against the description.

An image-reference tag inserted in the composer using the thumbnail’s @ action
video task with the leaf-canopy reference, motion description and ten-second settings

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Text and story scripts: make each game shot clear

Text is both a creative note and a generation input. Fix character traits and the story’s purpose first, then split a long story into individual shots to reduce conflicting instructions.

Choose a small story

Open a project with a one-sentence premise, one character and one location. Start with a three-shot story instead of putting an entire world description in a single request.

Mushroom Shop story brief, fixed character traits and three shots

Write a brief in a text node

Double-click an empty area and choose Text. To write a brief yourself, choose Write your own content on the empty card. Describe visible events, fixed character traits, time of day and palette in the body. For longer text, use Expand editor in the text toolbar to review the premise and individual shots together.

For AI writing, enter the writing or script requirements, check the credit quote and generate. Review and edit the generated body. Downstream references use the body, not the AI prompt input.

Write a three-shot opening for a warm exploration game. A girl wearing a teal scarf discovers a mushroom shop in a forest at dusk. For each shot, list shot size, visible action, environmental details and mood. Keep one main action per shot.

Split the script into separate shots

Number shots and give each one a subject, shot size, action and background. Still images describe a visible state; video describes change over time. Replace abstract traits such as “brave” with visible actions such as “reaches out to open the wooden door”.

  1. Shot 01: wide view, the girl follows a forest path toward warm light.

  2. Shot 02: medium view, she stops outside the mushroom shop.

  3. Shot 03: close view, a hand opens the door and orange light spills through.

Keep character and scene rules together

Add a “Fixed traits” text node for scarf color, clothing, hair and shop shape. Repeat essential constraints in each shot, and use the same character reference to reduce variation.

Text reference support depends on the destination model. Include key instructions in the generation node too, so they do not remain only in a note outside the request.

Review before generating

Read the script for actions that fit within one shot, a logical sequence and abstract instructions that cannot be shown. Change one problem at a time, then use the revised description in an image or video node.

Use the reviewed script in image or video nodes. When changing a character or plot, update the fixed brief and affected shot descriptions together to avoid conflicting instructions.

Check what the image communicates

Compare each generated shot with its script. Confirm character traits, action direction and time of day before producing the next shot.

Practice: write one visible description for each of three shots that works without narration. If the sequence needs extensive explanation, simplify the story or add a clear transition.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to write a story
Back to illustrated tutorials

Image node tools

Features: panorama, viewpoints, lighting, image editing, splitting and groups

After generation, refine a viewpoint, lighting or local detail. Identify whether the issue is composition, color or structure before choosing a tool.

Keep the original and compare viewpoint, lighting and local edits separately. Solve one problem at a time before continuing.


How to use image tools

Select a populated image node for its toolbar. Tools can be pinned or found in More editing; availability depends on resource readiness.

image node and image toolbar

Panorama

Explore a surrounding scene

Use Panorama to prepare a surrounding scene and inspect its directions. The result is not automatically a physically accurate 3D space.

generated floating-island panorama and fullscreen controls

Tips for useful results

  • Use a scene with clear depth and a readable ground, subject and background.

  • Review spatial continuity:

    • Inspect seams and stretched regions.

    • Choose readable views for later references.

How to use it

Where to start

  • Open Panorama from the image toolbar or More editing.

  • Select an environment reference and generate a panorama. Review its field of view, seams and object shapes in the preview.

    floating-island environment reference used for panorama generation
    generated floating-island panorama and fullscreen controls

What can you do with a panorama?

  • Explore directions: inspect different views for seams and spatial distortion.

    A changed viewing direction after dragging the panorama
  • Capture: use the current view or available multiple-view captures for references.

    Four views exported from the same panorama and grouped on the canvas
  • Composition guides: review subject placement and the horizon.

    Composition guides enabled in the panorama preview
  • Reset the view: return to the initial direction for comparison.

    generated floating-island panorama and fullscreen controls

Multiple viewpoints

Change the view and compare silhouettes

  • Use a preset or rotation and tilt to generate a new 2D viewpoint from the source. It is not a freely rotatable 3D model.

    generated sign viewpoint saved on the canvas

How to use it

Viewpoint settings

  • Choose a front, side or overhead goal and keep the subject complete.

  • Use available presets or rotation and tilt sliders: rotation -90° to 90°, tilt -75° to 90°.

    Rotation, tilt and camera settings in the viewpoint panel

Additional prompt guidance

  • Describe framing, fixed parts and background extent, then inspect structural consistency.

    three-quarter viewpoint settings, sign constraints and quote

Example: Preserve the wooden sign, mushroom canopy and hanging lantern. Use a three-quarter viewpoint with a complete prop and simple background, adding no parts or lettering.

Viewpoint presets

  • Choose a current preset and review settings and quote. Compare accessories, proportions and occlusion against the source.

    viewpoint panel after selecting the Side preset

Lighting

Shape materials and mood with light

Relighting provides direction, brightness, color and rim light. Smart mode adds descriptions, reference images and presets. Review the generated wood grain, shadows and lantern details.

sign result after parameter-based relighting

How to use it

Direction and rim light

  • Turn off Smart mode to adjust the key direction and enable rim light when needed.

  • Keep the subject and viewpoint fixed while comparing light, without changing material and composition together.

    key direction, brightness, warm color and rim-light controls

Brightness and shadows

  • Adjust brightness gradually and inspect tonal transitions and shadow edges.

  • Check clipped highlights and lost shadows, keeping the same input for comparison.

    key direction, brightness, warm color and rim-light controls

Color

  • Set the light color and distinguish it from the material’s own color.

  • Check that character colors and key accessories remain recognizable.

    Warm hexadecimal light color in the color picker

Presets, descriptions and references

  • Turn off Smart mode for direction, brightness and color. Turn it on for presets, descriptions or reference images.

  • A description can state mood, main light direction and fixed subject traits.

    Example: Keep the mushroom roof, wooden arrow and right-hand lantern. Use warm side light on the wood grain, retain moss and trunk detail in shadow and keep the viewpoint fixed.

  • In reference mode, verify the added image and review the quote before submitting.

  • Presets help explore a direction, but their results still need comparison.

    Eight preset entries in the relighting panel
    smart-lighting description, reference-image entry and presets

Grid art and sprite sheets

For grid assets, make cells and spacing clear before splitting. Sprite sheets also need stable scale and baselines before game use.

uploaded nine-cell prop image node

Basic image editing

Image processing tools and the separate Image edit workspace serve different needs. Open the appropriate current toolbar entry.

  • Upscale: review settings and quote before generative enhancement.

  • Resize: change the 2D image dimensions for the intended use, then check clarity.

  • Outpaint: extend the image and inspect the join.

  • Inpaint: select an area with brush, rectangle or lasso, then describe its change.

  • Cutout: remove an image background and inspect transparent edges.

  • Crop: change the retained area without reconstructing hidden content.


Split a grid

Split a grid into independent assets. Set cells from the actual boundaries and check that no subject is cut off.

grid-splitting menu and nine-cell source
3×3 boundaries, row and column counts, and selected cells

How to use it

  • Open grid splitting from the toolbar or More editing and set the grid.

  • Review boundaries and previews before outputting the selected slices.

  • Check transparency, padding and completeness in every slice.

    Selecting an individual cell in the grid editor
    Nine sliced image nodes grouped on the canvas

Local notes and edits

Describe the exact area to change

  • Open Inpaint from More editing and specify the region, replacement and details to preserve. For example, replace a sign’s mushroom canopy with leaves while keeping the board and lantern.

  • Choose the edit area with brush, rectangle or lasso and describe the change.

  • Compare both inside and outside the selection against the original; nearby details may also change.

    inpainting selection over the mushroom roof and leaf-replacement instructions
    leaf-canopy inpainting result generated from the selection and description

Rotate and mirror

  • Preview a 2D rotation or mirror, then confirm or cancel. Inspect lettering, accessories and handedness after a flip.

    horizontal-mirror preview with rotation, flip, confirm and cancel controls

Image groups

Compare references and results together

Group related images and label references, experiments and final versions so you can move them together and compare results.

Reference, generated result and layout controls in an image group

How to use it

Create a regular group

  • Select related images and group them as references, trials and approved work.

    Group and Arrange toolbar for multiple selected images

Organize an existing group

  • Name references, trials and approved work separately and inspect their connections.

    image inputs, outputs and reference connection within a regular group

Organize sliced outputs

  • Keep reusable slices as independent assets and group them by purpose.

    Nine sliced image nodes grouped on the canvas

What to review after grouping

  • Image order, names and reference connections are clear.

  • Review occlusion, incomplete edges and connections in decomposed assets; they are not automatically hand-finished layers.

    Five identified sign parts and output settings
    Five generated sign parts grouped on the canvas

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Video node tools

Features: video enhancement, retakes, continuation, frame extraction, capture and trimming

Enhance an existing clip, revise selected ranges or create a continuation. Keep the source before choosing a follow-up tool.

Select a ready video and choose Enhance, Retake, Continue, Trim or Extract frames from its toolbar. Pick the tool that addresses the problem you want to solve.


Video enhancement

Choose Enhance, then an available model and resolution. Interpolation, target frame rate and slow motion depend on the selected option.

Review source details and quote before submitting. Inspect detail, edges and motion afterward; enhancement does not guarantee corrected geometry.

Topaz enhancement panel: 1080P, no interpolation, 1x and quote
completed ten-second 1920×1080 enhancement result

Retake a segment

Describe changes for a selected time range

Open Retake and describe each selected range separately. Current sources are 4–30 seconds, with up to five ranges of at least four seconds each.

Review the range, prompt and quote before generating. For example, select the second half and request gentle movement in the lantern and leaves. Review both the edited section and the surrounding video and audio.

retake range, video reference, instructions and quote
completed ten-second retake result saved on the canvas

Video continuation

Choose Continue from the Retake menu and select at least four seconds of reference video. Describe what happens next; for example, use seconds 0–4 and request a gentle push-in with moving leaves and lantern, with a five-second 720P output.

Continuation requests new footage after the selected range. It does not automatically join the source and result; review character, scene and motion continuity.

selection of the zero-to-four-second continuation reference
continuation reference tag, next-action instructions and five-second settings
generated five-second continuation as a separate clip

Extract and review frames

Inspect movement frame by frame

Choose a range and interval in Extract frames to inspect motion as still images. For a four-second, 30 FPS clip, sample every 24 frames, then choose which images to keep and export.

extraction range and 24-frame sampling interval for the four-second mushroom-sign source
Six extracted candidate frames in the frame editor

Trim a clip

Open Trim from the video toolbar and preview the selected range. For example, save seconds 0.5–3.5 of a four-second clip as a new video while preserving the original. Review the output duration, first and last frames, and audio.

trim range set to 0.5–3.5 seconds of the four-second source

Trim and review

  • Choose a stable start before the action.

  • Keep a short hold after the action without cutting it off.

  • Preview the range before confirming the output.

  • Use current-frame capture for stills or frame extraction for animation assets.

    completed trimmed result of approximately 3.1 seconds
    Independent image node captured from the uploaded four-second source

Motion references

Use motion references to clarify movement

To reuse motion, choose a model that accepts video references or prepare a reference with the motion tools. Describe the action and timing you want to preserve.

How to use it

Choose a reference

  • Check the model’s accepted reference types, then choose readable character and movement assets.

    four-second mushroom-sign video and video toolbar
    Independent image node captured from the uploaded four-second source

Prepare movement or camera references

  • Use existing footage or the available Motion and Pose editor. A preview is not a completed character film.

    selection of the zero-to-four-second continuation reference
    continuation reference tag, next-action instructions and five-second settings

Use it downstream

  • Add the reference, describe the motion and camera to preserve, review settings and quote, then inspect the full output.

    retake range, video reference, instructions and quote
    completed ten-second retake result saved on the canvas

Silent video and sound assets

Frame-sequence MP4 exports omit the original audio; preview and export frame rates are separate settings. Six images at 2 FPS make a three-second clip. Prepare dialogue, music and sound effects separately when needed.

sequence-video export format, 2FPS and 1280×720 settings
silent three-second video exported from six frames at 2FPS

Plan voice and background sound

There is no voice or background-stem extraction tool here. Retain separate dialogue, music and effect sources for an appropriate editing workflow.

Text, voice and generation settings in the separate speech node
uploaded twenty-second music asset and audio toolbar

Organize assets for editing

Organize processed clips in shot order and select the usable versions before editing a finished sequence. Use a video editor for multitrack audio, transitions and subtitles.

Source clips, processed results, separate speech and music in the video-tools canvas

What to hand off

  • Name approved clips in shot order.

  • Check boundaries, movement and aspect ratio.

  • List dialogue, music and effects separately.

  • Record outstanding issues; task success is not content approval.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Audio node tools

Features: trimming, speech speed, music, effects and text to speech

Music sets mood, effects mark events and speech reads words. Start with an existing audio asset or create one in the matching node.

Choose trimming, speech settings or generation tools according to the sound’s purpose. Keep the original so you can compare timing and volume.


Trim audio

Select a ready audio node and choose Trim. Listen before setting a range with natural onset and decay.

Avoid cutting through words, key sound effects or musical phrases. For example, keep seconds 2–10 of a twenty-second track and save an eight-second clip.

two-to-ten-second trim range and waveform in the twenty-second music source
eight-second music segment trimmed and saved on the canvas

Speech speed

Existing audio has no standalone speed tool. To change narration pace, adjust speed in Speech generation before generating again.

Speech speed and volume range from 0.5 to 2; pitch ranges from −12 to 12. Try a short sentence at speed 1.2, volume 1 and pitch 0, then adjust for the dialogue’s rhythm.

speech settings: speed 1.2, pitch 0 and volume 1

Choose and organize segments

Listen and mark the start and end times for each segment, then trim and name them separately. Keep a note of each clip’s purpose and source file.

Use consistent names for dialogue, music and sound effects. Group them by shot or use so they are easy to edit and replace.

Practice: retain the source music and organize its two-to-ten-second segment separately from speech. Check the boundaries for abrupt cuts.

Source music, trimmed segment and separate speech versions in the audio canvas

Speech generation

Turn approved dialogue into a sound asset

What it does

Current SeedAudio 1.0 accepts up to 2,000 plain-text characters, with no resource references, voice selection or cloning. Enter the words to speak, not stage directions.

How to create speech

  • Create Speech generation and enter approved dialogue.

  • Choose sample rate and format, then speed, volume and pitch.

  • Review the quote and test a short sentence before the full text.

    plain-text dialogue, SeedAudio 1.0, 24kHz MP3 and generation quote

Generate and review

  1. Prepare text: review punctuation, numbers and pauses.

  2. Choose output: 8, 16, 24 or 48 kHz; mp3, wav, pcm or ogg_opus.

  3. Listen: inspect pronunciation, clarity, phrasing and volume.

  4. Organize: name the approved version and keep it separate from music and effects.

Example dialogue: Welcome to the forest shop. Follow the wooden arrow and let the warm lantern light your journey.

speech waveform, player and dialogue generated at speed 1.2

Music and effects have separate nodes. SeaArt effects currently allow 1–5 seconds; music duration follows the current model options. Listen at the intended playback volume.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Image generator

Features: explicit descriptions, style references, local edits and composition

References and precise descriptions help guide an image. Name the traits to preserve before choosing a model and settings.

Define the subject and details to preserve, then refine style, local edits and composition separately. Change one aspect at a time to see which instructions work.

Element references

Identify what to preserve

Add images to the reference list and identify the subject, materials, accessories and details you want to preserve or change.

How to use it

  • Create an image node and verify the source reference. After selecting it from the canvas, close the selection toolbar before generating.

  • State what to preserve and change; crop a clear reference if only one part is needed.

  • Choose a reference-capable model and review ratio, resolution and quote.

    source reference, edit description, image model and quote

Style references

Align the brief with a visual direction

Use style-library and image references to align colors, materials and shapes. Choose a compatible model and check its reference types and limits.

How to use it

Use the library or a style reference

  • Open Style library at the bottom of the canvas, browse tags and choose Use. For isometric game props, try the Western isometric scene objects preset.

  • Keep the preset reference and add the original mushroom sign. Request its blank arrow board, trunk base and lantern on the right.

  • For example, choose SG Image 2, 1:1, 1K, standard quality and one output. Review the current quote, then compare the result with the original.

    style-library views, tags and preset cards
    isometric-objects style reference, source sign and SG Image 2 settings
    sign generated with the style-library reference and saved on the canvas

Keep your own style references

Save a cohesive set of reference images in My styles for reuse. Clear colors, materials and shapes help communicate the visual direction.

How to organize them

  • Choose Create style in My styles, enter a recognizable name and add one to three images from upload or generation history. For example, save the sign reference as Forest shop · Isometric sign reference.

  • Save the entry and find its card in My styles. Hover to reveal Use, then review the current model, reference count and quote when reusing it.

    Private-style form with a name and sign reference
    saved entry in My styles, hovered to reveal Use

Local detail and close views

Choose an area before describing a change

Use Inpaint for local changes. To inspect a detail, crop it or specify the area you want shown in close-up.

How to use it

  • Select the image, open Inpaint and choose an area with brush, rectangle or lasso.

  • Describe the edit: replace the mushroom roof with a leaf canopy, preserving the blank arrow board, trunk, small lantern on the right and background.

  • Inspect both inside and outside the selection against the original.

    mushroom-canopy selection and leaf-canopy inpainting description
    completed leaf-canopy sign from Inpaint

Viewpoint and composition

Guide the image with clear camera language

Describe framing with terms such as front, side, overhead, close-up and wide-angle, along with subject size and background coverage. Use Multi-angle to explore another view of an existing image.

How to use it

  • Specify subject size, viewing direction and background extent.

  • For example, choose a three-quarter view and request the same sign structure. Review the current quote, then inspect accessories, proportions and occlusion in the result.

    three-quarter-view input and quote in Multi-angle
    sign viewpoint generated by Multi-angle

Example direction

  • Workflow: keep the original fixed and try style references, Multi-angle and Relighting separately. Arrange the results side by side to compare each change.

  • Prompt: Preserve the complete wooden sign, mushroom canopy and small lantern hanging on the right. Use a three-quarter view, keep the subject complete and the background simple, and add no parts or lettering.

  • Review the original, three-quarter view and warm-light result in order. Check proportions, edges, part connections and readability at small sizes.

    original mushroom sign before Multi-angle and lighting
    sign viewpoint generated by Multi-angle
    warm-light result for reviewing the sign, lantern and shadows

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

Video generator

Features: reusable character references, Omni reference, first/last frames and camera descriptions

For consistency, keep references and character traits stable. For camera motion, separate subject movement from the camera’s change.

Prepare character references and camera instructions separately. Establish a stable appearance before adding camera motion so you can identify what needs adjustment.

Character references for video

Reuse a consistent visual reference

Reuse a clear approved character image in later video nodes. A reference guides output without guaranteeing identical identity, clothing or every detail.

Prepare character references

  1. Upload a complete character image and check the face, outfit and accessories. Keep front, side and rear views for comparison, then add references suited to the intended shot.

    original robot-stage reference saved on the video canvas
    original robot triptych on the canvas for inspecting appearance
  2. Create Video from Add node and add the character reference. Close the canvas selection toolbar after choosing it. For example, use Seedance 2.5 in Omni reference mode for a robot shot.

    robot reference, subject and camera prompt, and four-second video settings
  • Use a concise description of the character’s colors, outfit and props, and state which traits should stay consistent during motion.

  • After changing models, recheck reference types, counts, duration, ratio and resolution. Try a four-second, 16:9, 720P motion test and disable generated audio when it is not needed.

    16:9, 720P, four-second settings with generated audio off
  1. Describe subject and camera movement, review the current quote and generate. For example, keep the robot still while the camera orbits about 15 degrees to the right with a slight push-in. Watch the complete result for consistency.

    completed robot orbit video node and player

Camera motion

Separate subject movement from camera movement

When requesting a push-in, pull-back, lateral move or orbit, also define the subject action. Test a fixed camera before adding movement.

How to direct motion

Common camera descriptions

  • Fixed: small subject action, camera remains in place.

  • Push-in: approach the subject slowly while preserving direction.

  • Lateral: move slowly in one direction without complex rotation.

    robot reference, subject and camera prompt, and four-second video settings
    completed robot orbit video node and player

Write your own camera direction

  • Save useful directions in Text nodes, separating camera motion, subject action and details to preserve. Name each shot so you can reuse and refine its instructions.

  • Example direction: a green leaf-canopy shop sign is the only subject. Push in slowly and steadily with subtle movement in the leaves and right-hand lantern. Preserve the blank arrow board, trunk, mossy base, cream background and materials. No deformation, added objects or lettering, cuts, dialogue or music.

    Camera-direction notes for the robot orbit and sign push-in
    Reference, prompt and settings from the leaf-canopy sign push-in task

Camera direction tips

  • Keep framing and movement compatible; a tight close-up conflicts with a broad aerial view.

  • Reduce motion when deformation appears and change one subject or camera dimension at a time.

  • First & last frames is model-specific and accepts at most two images. Matching endpoints do not guarantee a seamless loop.

  • Inspect faces, hands, background drift and object changes before trimming or regenerating.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create
Back to illustrated tutorials

3D Director

Features: scene building, character poses, cameras and framing, movement paths, keyframes, photo and video export

Arrange characters, props and cameras in the director, then send photos or animated previs to the canvas as references. Start with one character, one prop and one camera to learn setup, framing and export.


Overview

Build the scene before choosing the shot

Use the asset library and outliner on the left, the observation viewport for placement, camera preview for final framing, the right inspector for properties and the bottom timeline for motion. Edits save with the project; confirm the synced status before leaving.

director library, viewport, camera preview, timeline and inspector

What can the director help with?

  • Review placement and scale with a roughly 177.5 cm character and a 70 cm cube. Compare depth, occlusion and subject size.

    spatial relationship of the waving character and yellow prop
  • Compare editing and output views: the observation viewport is for editing; preview and export use the chosen camera.

    observation view alongside the 16:9 camera preview

Build and export a set ✨

Open the director

  1. Open a project canvas, choose Add node and select Director in the tools section.

  2. Choose Enter set on the new node. Use Return to canvas in the upper right to leave the editor.

Director node and Add node entry on the canvas

1. Add characters and scene objects

  • Choose a character, geometry, building, plant or rock in the asset library, then click in the observation viewport to place it. Lights and cameras have their own categories.

  • Begin with a few objects: keep the initial character and lighting, then add a yellow cube beside the character.

  • The current library uses built-in assets; account model uploads and My models are not enabled. The separate 3D model guide covers standalone generation and preview.

director asset library and geometry category

2. Adjust position, orientation and size

  • Select an object in the viewport or outliner, then move, rotate or scale it with the tools or inspector. Positions, dimensions and movement increments display in centimetres; rotations display in degrees.

  • Scale 1 preserves the intended physical size. Place a 70 cm cube at X = 120 cm for practice. Establish object size before changing camera distance; use Ground object to align its bottom.

  • Use the outliner to manage names, visibility, locks and groups. Check the selection before editing lights or cameras.

character transforms and physical dimensions with cm and degree units

3. Set camera position and framing

Camera view: select a camera in the outliner and adjust its frame, projection, position and FOV. Check subject coverage in camera preview; start with 16:9 and a 45° FOV.

camera framing, position, orientation, projection and FOV controls

Observation view: pan with the middle button, orbit with Alt/Option plus left drag and zoom with the wheel. Observation navigation is separate from the authored camera; check camera preview after navigating.

Different framing in the observation and output camera views

4. Capture a photo for canvas creation

  1. Select a camera, choose Control camera and review its framing, then click Photo. The completed photo uploads into an image node on the current canvas.

  2. Press Esc to leave control mode and inspect the photo on the canvas. Add it to a supported image or video task and describe the placement, viewpoint and action to preserve. Review model support and pricing before submitting an AI generation.

Photo action in the camera-control viewport
photo and exported video saved as canvas nodes

Advanced workflows

Character pose controls

Choose a pose and inspect the silhouette

Select a character and choose a preset under Character pose. Try Wave, then inspect the arms, body and prop from several angles before taking a photo.

Wave pose applied to the director character

Panorama and environment settings

Align the environment with the set

Open 720 Panorama on the toolbar and add an image from the canvas, generation history or local upload. Use a complete 2:1 equirectangular panorama, then align its radius, position and rotation with the horizon. A flat camera background is configured separately in camera properties.

Review placement against a simple background before adding an environment and aligning its horizon. The panorama provides background context; scene objects determine occlusion and ground placement.

director panorama source picker
Panorama radius, position and rotation settings

Character and camera movement

Separate subject and camera movement

Expand the timeline and set its frame rate, duration and current frame. Resource tracks store property changes; path tracks move resources along a curve. Try a three-second, 30 FPS timeline with camera position keys at frames 0 and 89.

character path and timing on the timeline

1. Character movement path

  1. Select the character and choose Create movement path. Its current position becomes the start; click additional points in the viewport, then finish with Enter or Finish drawing. Esc cancels.

  2. Set start time, duration, facing direction, upright orientation and smoothing in path properties. Start with a three-point path lasting about three seconds before adding more turns.

  3. Play or scrub the timeline to check for intersections, abrupt turns and floating. A path controls position and orientation; review body pose and limb movement separately from travel through the scene.

three-point character path and editable properties

2. Camera movement

The camera library offers push, pull, lateral and orbit presets. Alternatively, select an existing camera, change its position at different times and record keys with the diamond beside the parameter.

camera movement preset library
  1. At frame 0, place the camera at X 300, Y 200, Z 400 cm and record a position key.

  2. At frame 89, move it to X 250, Y 200, Z 350 cm and record another key. Play back while checking the character, prop and framing.

camera position keys alongside the separate character path

3. Bind an observation target

Switch the camera to Target mode, choose Select model under Observation target and click the character in the viewport. Once bound, the camera keeps aiming at that character as it moves.

Target-mode camera bound to the character
  • The observation target controls aim; camera position still comes from its own keys or path.

  • Check subject scale and occlusion at the start, middle and end; adjust camera position and FOV when needed.


Controls and shortcuts

Q/W/E/R select, move, rotate and scale; F focuses a resource or the scene; Esc exits control or cancels. Pan with the middle button and orbit with Alt/Option plus left drag. Hold a mouse button to navigate with WASD and Q/E. Parameter fields retain normal typing. Open Shortcut help for platform-specific chords.

director shortcut help on macOS

Export video and hand off references

  1. Choose Export video and select a camera or an existing storyboard sequence. Review its source range, framing, long-edge resolution and frame rate; the source range determines the exported duration.

  2. For example, choose a camera, 1280×720 and 30 FPS. Select Export to canvas and keep the page in the foreground until it completes. The browser prefers MP4 and falls back to WebM when needed.

  3. Return to the canvas and review the photo and video nodes before generation or handoff. Name each output and note its camera so you can pair it with the script, references and shot list.

Export source, range, 1280×720 resolution and 30 FPS settings
completed video export added to the canvas

Try it yourself

Add a Director node, build a scene, frame it and export.

Open Projects to build a set
Back to illustrated tutorials

3D models and multiple views: start with clear references

3D inputs need to communicate shape clearly. Practice with a simple prop before complex characters. A 2D viewpoint image and a 3D model are different outputs.

Choose an object with a clear silhouette

Open a project and describe one complete wooden chest, including its lid, lock and four short feet. For single-image practice, prepare a clean reference with clear connections rather than multiple objects and complex lettering.

Chest prompt, Tripo text-to-3D settings and generation quote

Create a 3D node and choose its mode

Choose 3D Model from Add node, then select a model that supports text, a single image or multiple views. Start with a simple prop described in text before adding image references.

Choose geometry quality, target face count, textures and PBR settings for the intended use. For example, request triangles, 8,000 faces and 4K textures for a chest. Review the current quote and inspect the completed mesh; the actual face count may differ.

A simple forest shop treasure chest, rounded wooden box, arched lid, two brass hinges, one square lock in the center, four short feet, one complete standalone object, stylized game prop.

high-fidelity, detailed geometry, triangles, requested 8000 faces, 4K texture and PBR settings

Use separate images for multiview

Use separate images for each view. Place the front image in Front and the right image in Right, then add any other required views. Keep the object, scale, materials and background consistent; a collage is not a set of independent references.

When preparing references with Multi-angle, check silhouettes, part counts and connections in every image. Its 2D outputs may disagree across views; fix inconsistent references before generating a 3D model.

separate front and right references in a multiview draft

Rotate the preview to inspect hidden sides

Open the completed model in the full viewer and inspect front, back, bottom and side views. Use triangle, vertex and mesh statistics to assess complexity for the intended use. Check holes, thin surfaces, locks, joints and feet, especially on hidden faces.

front view of the GLB chest with 6893 triangles and 5729 vertices
rear view of the GLB chest for inspecting the body and connections
underside view of the GLB chest for inspecting its four feet and base

Choose follow-up work for the destination

Use available retopology, rigging or texture tools according to the intended use. Decide whether the result is a static prop or an animated character before running additional tasks.

Choose an export format from the node toolbar. For use in another 3D application, check that the GLB includes the required materials and textures. Verify scale, orientation, materials and mesh after import, then assess performance and animation needs.

node-toolbar export menu with GLB selected and FBX and OBJ options

Compare the model with the references

Review silhouette, part count, symmetry and material regions. Record defects before adjusting inputs or trying an available model. One prompt change will not necessarily fix every mesh issue.

Practice: try text and single-image input for the same chest. Compare its back structure and lock detail, then decide whether preparing separate multiview images is useful.

Try it yourself

Open your projects, create a canvas, and apply this tutorial to your own work.

Open Projects to create a 3D model