Hashtag Aesthetic: Building a 20-Second Animated Comedy in Creative Studio
How one line of chat became a two-scene, dialogue-driven animated comedy — the exact brief, character cards, and shot prompts Creative Studio generated, start to finish.
5 min read
Every tutorial on this blog starts the same way an actual project does: with the raw output of Creative Studio, unedited. This one walks through “Hashtag Aesthetic” — a 20-second, two-scene animated comedy about a prince, a princess who won’t put her phone down, and a dragon with a crown fetish — following the actual steps: a one-line chat brief, the timeline it built, sending that to the director, and the exact prompts Produce generated from it.
The brief
Creative Studio doesn’t ask for a script up front — it asks for the smallest brief it can work with, and builds on it through conversation. Here, one message was enough: the chat proposed exactly the two 10-second segments with 3-4 second shots we asked for, and the timeline showed that structure before anything was finalized. Here is the entire brief that started this piece:
I need a 20-second funny prince and princess cartoon with dialogue. I need 10-second clips, and every clip should have 3-4 second shots within it.
That’s it — no genre picked from a list, no character bios, no scene count typed by hand. We checked the timeline it built, it already matched the brief, so there was nothing to reshape — straight to Send to the director. That’s the step that turned it into a full treatment: a two-character-plus-one-dragon cast, an emotional arc for each segment, dialogue for every beat we asked for, and its own decision, unprompted, to render each segment as one continuous “storyboard” shot instead of three separate clips. More on why in the next section.
The cast
Before any shot renders, Creative Studio’s producer turns each named character into a locked reference sheet: four views of the same person, side by side, so the video model has faces to match against instead of a name to guess from. Three cards came out of this brief.
Reference definitions
- Voice
- Resonant, slightly theatrical, medium pace, Standard British (RP)
- Wardrobe
- Ornate, but slightly impractical royal attire.
- Signature detail
- A perpetually hopeful but easily discouraged expression
Hand-drawn 2D animation, visible linework and flat cel shading. Not photographic. Character reference sheet for Prince, Protagonist. male, young adult, fantastical, athletic, brown, neatly styled, Classic storybook prince, slightly pompous but endearing., Ornate, but slightly impractical royal attire., A perpetually hopeful but easily discouraged expression. Four views of the SAME person side by side on a plain neutral grey backdrop: full-body front, full-body back, full-body side profile, and a head-and-shoulders face close-up. Identical wardrobe, hair and proportions in every view. Even, neutral lighting. No text, no labels, no props, no background scenery.
Reference definitions
- Voice
- Modern, slightly casual, upbeat, quick pace, General American
- Wardrobe
- Flowing, royal gown, practical for movement.
- Signature detail
- Always has her phone subtly in hand or nearby
Hand-drawn 2D animation, visible linework and flat cel shading. Not photographic. Character reference sheet for Princess, Protagonist. female, young adult, fantastical, slender, long, flowing, stylized, Elegant storybook princess, with a mischievous glint in her eye., Flowing, royal gown, practical for movement., Always has her phone subtly in hand or nearby. Four views of the SAME person side by side on a plain neutral grey backdrop: full-body front, full-body back, full-body side profile, and a head-and-shoulders face close-up. Identical wardrobe, hair and proportions in every view. Even, neutral lighting. No text, no labels, no props, no background scenery.
Reference definitions
- Voice
- a young man's voice
- Signature detail
- Obsessed with shiny objects, especially crowns.
Hand-drawn 2D animation, visible linework and flat cel shading. Not photographic. Character reference sheet for Sparky, Comedic foil/pet. male, young, fantastical, Small, fluffy, brightly colored cartoon dragon, with large, expressive eyes., Obsessed with shiny objects, especially crowns.. Four views of the SAME person side by side on a plain neutral grey backdrop: full-body front, full-body back, full-body side profile, and a head-and-shoulders face close-up. Identical wardrobe, hair and proportions in every view. Even, neutral lighting. No text, no labels, no props, no background scenery.
The treatment
With a cast locked, the director assembles a treatment: how many shots, how long each runs, who speaks when, and which render mode fits the material. For this piece it explained its own reasoning:
This structure directly implements the client's detailed timeline, ensuring each comedic beat lands with precision. The storyboard render mode for 10-second shots allows for rich, layered visual storytelling within the fixed segments, crucial for comedic timing and character interaction in a cartoon format.
The treatment doesn’t render on approval — it lands on a Review & edit screen first. Every change there re-runs the same checks for free, no model call, so most pieces (this one included) validate clean on the first pass; if something did need fixing, this is the point where it’s still free to fix. Only pressing Produce turns the approved treatment into the actual per-shot prompts below — read on for what came out.
The video model has no voice ID or seed — nothing that lets it recognize a character’s voice across cuts. So Creative Studio pins each character’s voice as one fixed description and repeats it, word for word, in every shot that character speaks in. This is the only reason Prince sounds the same in scene 2 as he did in scene 1:
| Character | Voice pin |
|---|---|
| Prince | Resonant, slightly theatrical, medium pace, Standard British (RP) |
| Princess | Modern, slightly casual, upbeat, quick pace, General American |
| Sparky | a young man's voice |
Voice pins — repeated verbatim in every shot
The shots
Two shots, ten seconds each, three storyboard panels apiece. Each shot renders in two passes, not one: first an image model draws a single board — three panels, side by side, one continuous piece of art — then the video model is told to animate that exact board from panel to panel. The board is the source of truth for faces, colours and composition; the video prompt only adds motion, camera moves and voice. Below is exactly what shipped to each model, in order.
Shot 1 — the pitch
Prince kneels with a rose and a rehearsed speech. Princess is on her throne, scrolling. Sparky watches from behind the throne.
Reference definitions
- Cast
- Prince, Princess, Sparky
- Panels
- 0–3s, 3–6s, 6–10s
Technical
- Aspect ratio
- 9:16
- Layout
- 3-panel grid, panel number + time range labelled only
- Image engine
- Nano Banana
A clean storyboard board: 3 equal-size photographic frames arranged in a tidy grid, read left-to-right then top-to-bottom, frames sitting edge to edge. Label each frame with ONLY its panel number in the top-left corner and its time range in the top-right corner. NO captions, NO shot descriptions, NO camera notes, NO subtitles, NO overlay text and NO logos anywhere in or under any frame — only the photographic image plus those two small labels. Hand-drawn 2D animation, visible linework and flat cel shading. Not photographic. Consistent look across every frame: Bright and vibrant cartoon aesthetic with clear, expressive character designs. Exaggerated motion and facial expressions to enhance comedic timing. Uses a soft, diffused lighting style to maintain a light-hearted, whimsical tone and emphasize the fantastical setting. Use the supplied character reference sheet(s) for Prince (REF_prince), Princess (REF_princess), Sparky (REF_sparky); the same face, hair, build and wardrobe in every frame. SHOT 1 — 0-3 Prince kneels dramatically, presenting a single perfect rose with an earnest expression. Princess is seated on the throne, visibly engrossed in her phone, a close-up on her thumb scrolling.. Slow dolly-in on the scene, with a subtle rack focus pulling from the prince to the princess's scrolling thumb, emphasizing her distraction. SHOT 2 — 3-6 Close-up on the Prince's earnest, hopeful face, holding the rose out expectantly. Princess glances up from her phone, a flicker of mild disinterest crossing her face before she feigns interest.. Dolly-in to a close-up on prince's face, then a quick, subtle pan right, landing on a medium close-up of princess's face as her expression shifts. SHOT 3 — 6-10 Princess takes the rose, still holding her phone, examining the rose with a calculating look. Sparky peeks from behind the throne, eyeing the rose with curiosity.. Dolly-out and subtly pan right, re-framing to a medium close-up that shows princess taking the rose, her phone prominent, and then revealing sparky peeking curiously from behind the throne's edge. Every frame is composed in 9:16, photographic (no illustration, no hand-drawn look), with consistent characters, wardrobe, colour palette and lighting throughout.
This is the image that gets animated in the next prompt — every face, prop and background in the final clip traces back to this board, not to the video prompt's text.
Reference definitions
- Cast
- Prince, Princess, Sparky
- Panels
- 0–3s, 3–6s, 6–10s
- Location
- A lavish, somewhat fantastical throne room.
Technical
- Aspect ratio
- 9:16
- Duration
- 10 seconds
- Render mode
- storyboard — 3 panels animated as ONE continuous clip
- Video engine
- Kling
Animate this storyboard board into a single seamless clip, moving through its panels in order over the full duration. Maintain the exact visual style, characters, colours and composition of the board — do not redesign anything. Motion and camera moves flow naturally from one panel to the next; it is ONE continuous clip that travels through every scene on the board, with no panel borders, gutters or grid visible in the output. The motion runs panel 1 (0-3): Prince kneels dramatically, presenting a single perfect rose with an earnest expression. Princess is seated on the throne, visibly engrossed in her phone, a close-up on her thumb scrolling., Slow dolly-in on the scene, with a subtle rack focus pulling from the Prince to the Princess's scrolling thumb, emphasizing her distraction.; then panel 2 (3-6): Close-up on the Prince's earnest, hopeful face, holding the rose out expectantly. Princess glances up from her phone, a flicker of mild disinterest crossing her face before she feigns interest., Dolly-in to a close-up on Prince's face, then a quick, subtle pan right, landing on a medium close-up of Princess's face as her expression shifts.; then panel 3 (6-10): Princess takes the rose, still holding her phone, examining the rose with a calculating look. Sparky peeks from behind the throne, eyeing the rose with curiosity., Dolly-out and subtly pan right, re-framing to a medium close-up that shows Princess taking the rose, her phone prominent, and then revealing Sparky peeking curiously from behind the throne's edge.. Character reference: the people are the ones in the supplied reference sheet(s) for Prince (REF_prince), Princess (REF_princess), Sparky (REF_sparky) — keep them identical to their sheet and to the board. Voice casting — fixed for the whole piece, identical in every shot: Prince (the man in Ornate, but slightly impractical royal attire): Resonant, slightly theatrical, medium pace, Standard British (RP). Princess (the woman in Flowing, royal gown, practical for movement): Modern, slightly casual, upbeat, quick pace, General American. Spoken on the panels, in order: At 0-3, Prince (the man in Ornate, but slightly impractical royal attire) says, "My dearest Princess, for thee, I've battled dragons!" — only Prince's lips move. At 3-6, Prince (the man in Ornate, but slightly impractical royal attire) says, "And penned a sonnet, for your beauty!" — only Prince's lips move. At 6-10, Princess (the woman in Flowing, royal gown, practical for movement) says, "Aw. Cute. Is it, like, sustainably sourced?" — only Princess's lips move. Spoken dialogue only, exactly as written and only from the named speakers. No narration, no voiceover. Every person on screen who isn't the named speaker keeps their lips closed and still. Rendering constraints: Clean, unmarked frame — no watermarks, no captions, no subtitles, no UI overlay. Surfaces and signage stay free of lettering. Solid objects — furniture, walls, props — are impenetrable: people move around them, never through them, and every contact carries natural weight. Objects stay put unless someone deliberately moves them. Gravity behaves normally and camera moves stay smooth and coherent. Aspect ratio 9:16. Duration 10 seconds. Ends on a cut.
REF_prince / REF_princess / REF_sparky point back at the character cards from the previous section — the render pulls faces from those sheets, not from the text describing them.
Shot 2 — the selfie
Same throne room, one beat later. Confusion turns into a selfie op, and the prince’s grand gesture gets recontextualized as a prop.
Reference definitions
- Cast
- Prince, Princess, Sparky
- Panels
- 0–3s, 3–6s, 6–10s
Technical
- Aspect ratio
- 9:16
- Layout
- 3-panel grid, panel number + time range labelled only
- Image engine
- Nano Banana
A clean storyboard board: 3 equal-size photographic frames arranged in a tidy grid, read left-to-right then top-to-bottom, frames sitting edge to edge. Label each frame with ONLY its panel number in the top-left corner and its time range in the top-right corner. NO captions, NO shot descriptions, NO camera notes, NO subtitles, NO overlay text and NO logos anywhere in or under any frame — only the photographic image plus those two small labels. Hand-drawn 2D animation, visible linework and flat cel shading. Not photographic. Consistent look across every frame: Bright and vibrant cartoon aesthetic with clear, expressive character designs. Exaggerated motion and facial expressions to enhance comedic timing. Uses a soft, diffused lighting style to maintain a light-hearted, whimsical tone and emphasize the fantastical setting. Use the supplied character reference sheet(s) for Prince (REF_prince), Princess (REF_princess), Sparky (REF_sparky); the same face, hair, build and wardrobe in every frame. SHOT 1 — 0-3 Prince's confident posture slightly deflates, confusion on his face. Princess turns the rose, adjusting it slightly, then brings her phone up to eye level, framing the rose against a regal background.. Locked-off sticks, static. SHOT 2 — 3-6 Princess angles the rose and her face for a selfie, a practiced, performative smile. Sparky, now on the armrest of the throne, tries to sniff the rose, momentarily distracting the Princess.. Locked-off sticks, static. SHOT 3 — 6-10 Prince collapses onto one knee, utterly defeated, head bowed. Princess poses dramatically with the rose, pushing Sparky gently away, ready to snap the photo. Text overlay appears related to social media.. Locked-off sticks, static. Every frame is composed in 9:16, photographic (no illustration, no hand-drawn look), with consistent characters, wardrobe, colour palette and lighting throughout.
Reference definitions
- Cast
- Prince, Princess, Sparky
- Panels
- 0–3s, 3–6s, 6–10s
- Location
- Still the throne room.
Technical
- Aspect ratio
- 9:16
- Duration
- 10 seconds
- Render mode
- storyboard — 3 panels animated as ONE continuous clip
- Video engine
- Kling
Animate this storyboard board into a single seamless clip, moving through its panels in order over the full duration. Maintain the exact visual style, characters, colours and composition of the board — do not redesign anything. Motion and camera moves flow naturally from one panel to the next; it is ONE continuous clip that travels through every scene on the board, with no panel borders, gutters or grid visible in the output. The motion runs panel 1 (0-3): Prince's confident posture slightly deflates, confusion on his face. Princess turns the rose, adjusting it slightly, then brings her phone up to eye level, framing the rose against a regal background., LOCKED-OFF STICKS / STATIC; then panel 2 (3-6): Princess angles the rose and her face for a selfie, a practiced, performative smile. Sparky, now on the armrest of the throne, tries to sniff the rose, momentarily distracting the Princess., LOCKED-OFF STICKS / STATIC; then panel 3 (6-10): Prince collapses onto one knee, utterly defeated, head bowed. Princess poses dramatically with the rose, pushing Sparky gently away, ready to snap the photo. Text overlay appears related to social media., LOCKED-OFF STICKS / STATIC. Character reference: the people are the ones in the supplied reference sheet(s) for Prince (REF_prince), Princess (REF_princess), Sparky (REF_sparky) — keep them identical to their sheet and to the board. Voice casting — fixed for the whole piece, identical in every shot: Prince (the man in Ornate, but slightly impractical royal attire): Resonant, slightly theatrical, medium pace, Standard British (RP). Princess (the woman in Flowing, royal gown, practical for movement): Modern, slightly casual, upbeat, quick pace, General American. Spoken across the clip, in order: Prince (the man in Ornate, but slightly impractical royal attire) says, "Sustainably...? It's from the Royal Gardens, tradition!" — only Prince's lips move. Princess (the woman in Flowing, royal gown, practical for movement) says, "Is it #organic #fairtrade? Important for my aesthetic." — only Princess's lips move. Princess (the woman in Flowing, royal gown, practical for movement) says, "Filter first!" — only Princess's lips move. Prince (the man in Ornate, but slightly impractical royal attire) says (muttering, defeated), "My life is a hashtag." — only Prince's lips move. Spoken dialogue only, exactly as written and only from the named speakers. No narration, no voiceover. Every person on screen who isn't the named speaker keeps their lips closed and still. Rendering constraints: Clean, unmarked frame — no watermarks, no captions, no subtitles, no UI overlay. Surfaces and signage stay free of lettering. Solid objects — furniture, walls, props — are impenetrable: people move around them, never through them, and every contact carries natural weight. Objects stay put unless someone deliberately moves them. Gravity behaves normally and camera moves stay smooth and coherent. Aspect ratio 9:16. Duration 10 seconds. Ends on a cut.
Try it yourself
Every prompt on this page is the exact text Creative Studio generated for this project — nothing trimmed, nothing cleaned up. Start your own one-line brief in the chat, check the timeline it builds, send it to the director, and once Produce finishes, paste the shots below into your video model in order.
Want prompts like these written for your own brief?
Paste your notes. PromptMotion writes the prompt.
Try it free