Mascot pose and expression library

Lock a mascot with a rules sheet, then build on-model poses, short loops, an ad and a web hero from one prompt template.

  • Use case 5 of 8
  • Checked Oct 16, 2026
Film coming soon

About this use case

Barley, the red panda cub of Crunchwell, an invented breakfast cereal brand, locked on a rules sheet, drawn in 15 poses and expressions, then looped and placed in a 4:5 ad and a web hero. Barley started as one image: a key visual of him on a box of Honey Hoops. The models and settings in this use case are as of October 2026.

See moreSee less
  • A rules sheet for Barley, an invented cereal-brand mascot, then 15 on-model poses, three loops, an ad and a web hero.
  • One fixed prompt block plus one slot per pose, from one turnaround, each pose returned with transparency.
  • The loops are most of the cost; preview one at low resolution before running the finals.
Step by step with an agent, through the Scenario MCP (7 steps)Hide the steps
  1. Connect the Scenario MCP

    Connect your agent and sign in once at mcp.scenario.com. Then tell it which Scenario team and project to use, so every file lands there.

  2. Give the agent the files

    The brand's key visual with the mascot in it. Upload it with upload_asset or give its asset ID. From then on, the approved turnaround is the only reference for every pose.

  3. Brief the agent: the turnaround

    Approve the turnaround before any pose, then sample the palette from it and write the keep and avoid lists.

    Prompt
    Make a turnaround with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst): referenceImages [key visual] as an array, width 2048, height 1152, quality "high". Quote the cost with a dry run first and wait for my go.
    
    Prompt, word for word:
    Character turnaround sheet for an original brand mascot of a breakfast cereal brand. The mascot is Barley, the red panda cub from the reference image: a small, round, plush red panda cub standing upright on two short legs. Russet-orange fur with a soft cream belly, a cream-white face mask with cream patches above the eyes and on the cheeks, cream-rimmed rounded ears, a small dark brown nose, large warm amber-brown eyes with two white highlights each, a happy closed-mouth smile, dark chocolate-brown arms and legs ending in rounded mitten paws with no fingers, a long fluffy tail with four cream rings. A chunky teal knitted scarf wrapped once around the neck, its knot and both fringed ends hanging on the character's left side. Four full-body views in one row, evenly spaced, same size, same height, standing on one baseline, neutral friendly pose with arms relaxed and empty paws: front view, three-quarter view facing left, side view facing left, back view (tail and scarf ends visible, no face). Plain warm off-white background (#FAF6EE), even soft studio light with a gentle warm key, a small soft contact shadow under each view. Style: premium animated-feature character render, soft individually groomed fur, warm morning light, appealing shapes that read at small size. No text, no labels, no numbers, no logos, no cereal box, no other characters.
    
    Show it to me and wait for my approval.
  4. The pose library from one template

    Every job repeats the same fixed block and changes only the slot line. Pilot the hardest pose first: fingers sneak in where mitten paws hold a prop.

    Prompt
    Make the poses with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst): referenceImages [approved turnaround] as an array, width 1024, height 1024, quality "high", background "transparent". Every prompt is the fixed block below, word for word, followed by one slot line.
    
    Fixed block and the first slot line, word for word:
    Draw Barley, the character from the reference turnaround sheet. Keep exactly: small round plush red panda cub, russet-orange fur, soft cream belly, cream-white face mask with cream patches above the eyes and on the cheeks, cream-rimmed rounded ears, small dark brown nose, large amber-brown eyes with two white highlights each, dark chocolate-brown arms and legs with rounded mitten paws, long fluffy tail with cream rings, chunky teal knitted scarf with its knot and fringed ends on the character's left side. No fingers, no visible teeth, no clothes other than the scarf. Premium animated-feature render with soft groomed fur and warm morning light. One character, full body, centered, no ground shadow, no text.
    
    Pose: waving hello. Front view, his right mitten paw raised high and waving, the other arm relaxed, a big closed-mouth smile.
    
    Pilot the hardest pose first, Barley hugging a cereal spoon as tall as he is, and show it to me. Then run fourteen jobs, one slot each, with wait: false and collect them with one jobs_wait: eight expressions (happy, laughing, surprised, thinking, sad, proud, confused, sleepy) and six poses (wave, jump, eating, presenting, cheer, running). Quote the cost with a dry run first and wait for my go.
  5. Check every pose and redo

    Accept when every pose shows the scarf knot and ends on his left, two highlights per eye and mitten paws, with no teeth or fingers. Reject a scarf on the wrong side or missing, fingers or teeth, a halo or glow around the cutout, or a change in fur or lighting style.

    Prompt
    Make one contact sheet and check each pose against those rules, one line per pose. Redo a failure once with one added sentence. For a halo, add, word for word:
    Crisp cutout edges: no glow, no halo, no motion blur, no dust or particles around him.
    For a pose facing right, run it facing left, as in the turnaround, and add, word for word:
    The scarf knot and fringed ends hang on the side nearest the camera.
    Then snap alpha of 250 and above to 255.
  6. Loop three poses

    Wan 3.0, the first recommendation, flagged the mascot twice in this run; Seedance 2.5 was next. Preview one loop in draft before the finals.

    Prompt
    Put the wave, jump and presenting poses on a flat warm off-white background (#FAF6EE) at 1280x720 and upload each frame with upload_asset. Animate each with Seedance 2.5 (model_bytedance-seedance-2-5): image and lastFrameImage set to the same asset ID, duration 5, resolution "720p", generateAudio false. Preview the wave first with draft: true (480p) and show it to me. Quote the cost with a dry run first and wait for my go.
    
    Prompt for the wave, word for word:
    Seamless loop. The camera is locked. The small cartoon mascot in the image waves its raised paw side to side twice, its body bobs gently, its tail sways and it blinks once, then it returns to the starting pose. It keeps its exact design, colors and scarf in every frame, with mitten paws and no fingers. The plain warm off-white background stays flat the whole time. Ends exactly as it starts. No new objects, no shadow, no text, no camera move.
    
    For the jump and presenting loops, change only the motion sentence.
  7. Measure, file and report

    Prompt
    Measure each loop: the RMSE between the first and last frame against the average change between two frames, and the teal pixel count in every frame (a frame with no teal means the scarf vanished). Tell me which loops pass. Then create a collection for Barley with the turnaround, the poses and the kept loops, and report the models, every asset ID and the total cost spent.
Step by step in the web app (9 steps)Hide the steps
  1. Generate the turnaround

    Create › Images › GPT Image 2.5 Sunburst, the key visual in Reference Images, 2048x1152, Quality high. Describe the shape, every color and the four views.

    Prompt
    Character turnaround sheet for an original brand mascot of a breakfast cereal brand. The mascot is Barley, the red panda cub from the reference image: a small, round, plush red panda cub standing upright on two short legs. Russet-orange fur with a soft cream belly, a cream-white face mask with cream patches above the eyes and on the cheeks, cream-rimmed rounded ears, a small dark brown nose, large warm amber-brown eyes with two white highlights each, a happy closed-mouth smile, dark chocolate-brown arms and legs ending in rounded mitten paws with no fingers, a long fluffy tail with four cream rings. A chunky teal knitted scarf wrapped once around the neck, its knot and both fringed ends hanging on the character's left side. Four full-body views in one row, evenly spaced, same size, same height, standing on one baseline, neutral friendly pose with arms relaxed and empty paws: front view, three-quarter view facing left, side view facing left, back view (tail and scarf ends visible, no face). Plain warm off-white background (#FAF6EE), even soft studio light with a gentle warm key, a small soft contact shadow under each view. Style: premium animated-feature character render, soft individually groomed fur, warm morning light, appealing shapes that read at small size. No text, no labels, no numbers, no logos, no cereal box, no other characters.
  2. Write the rules sheet in code

    Sample six palette swatches from the approved front view, not from the prompt. Then list keep (scarf knot and ends on his left, two highlights per eye, mitten paws, cream tail rings and ear rims) and avoid (teeth, fingers or claws, other clothes, ground shadow, text or logo).

  3. Turn the rules into a template

    One fixed block, one slot line. The turnaround in Reference Images, 1024x1024, Quality high, Background transparent.

    Prompt
    Draw Barley, the character from the reference turnaround sheet. Keep exactly: small round plush red panda cub, russet-orange fur, soft cream belly, cream-white face mask with cream patches above the eyes and on the cheeks, cream-rimmed rounded ears, small dark brown nose, large amber-brown eyes with two white highlights each, dark chocolate-brown arms and legs with rounded mitten paws, long fluffy tail with cream rings, chunky teal knitted scarf with its knot and fringed ends on the character's left side. No fingers, no visible teeth, no clothes other than the scarf. Premium animated-feature render with soft groomed fur and warm morning light. One character, full body, centered, no ground shadow, no text.
    
    Pose: waving hello. Front view, his right mitten paw raised high and waving, the other arm relaxed, a big closed-mouth smile.
  4. Pilot the hardest pose

    Barley hugging a cereal spoon as tall as he is, where fingers sneak in. Three routes were compared: GPT Image 2.5 Sunburst, Nano Banana 2.1 (no transparency) and the Emotion Sheet App.

  5. Run the batch

    Fourteen jobs, one slot each: eight expressions (happy, laughing, surprised, thinking, sad, proud, confused, sleepy) and six poses (wave, jump, eating, presenting, cheer, running), in parallel.

  6. Check every pose against the sheet

    One contact sheet, one line per pose against the keep and avoid lists. Re-run a failure with one added sentence (the jump's halo, the presenting pose facing right), then snap alpha of 250 and above to 255.

  7. Preview one loop, then run the rest

    The pose on the flat off-white background at 1280x720, then Create › Videos › Seedance 2.5, that frame as first and last frame, 5 seconds, audio off: preview in draft at 480p, then the finals at 720p. Wan 3.0 flagged the mascot twice, so move to the next recommendation.

    Prompt
    Seamless loop. The camera is locked. The small cartoon mascot in the image waves its raised paw side to side twice, its body bobs gently, its tail sways and it blinks once, then it returns to the starting pose. It keeps its exact design, colors and scarf in every frame, with mitten paws and no fingers. The plain warm off-white background stays flat the whole time. Ends exactly as it starts. No new objects, no shadow, no text, no camera move.
  8. Measure the loops

    First-to-last-frame RMSE against the average change between two frames: below that, the restart is invisible. Count teal pixels in every frame to catch a vanished scarf, and watch the tail.

  9. Drop Barley into the layouts

    Key the flat background from the loop frames and remove the cream fringe, then place Barley in layouts drawn in code: a 4:5 ad with the jump loop, a 16:9 web hero with the presenting loop.

Read the full article10 min read
CoursesLessonsBrowseMy learning