Skip to main content

Guide tool

Gemini Gemini
~5 min read Updated Jul 30, 2026

Animated infographics with Gemini

A two-phase workflow: first the static image in Sticker Art style with nano banana, then the looping animation with VEO. With the base prompt to copy.

The two-phase workflow

The idea is simple but you have to respect the order: you don't ask Gemini for an already-animated infographic. First you build the static image with the right style, then you turn it into a short looping video. Two phases, two models.

The two phases, in short:
  1. 1 Phase 1 (Static image): with nano banana you generate the infographic in B&W Sticker Art style, starting from a reference image for style and character.
  2. 2 Phase 2 (Animation): you pass the image to VEO and add looping micro-movements, only on the characters. The text stays still.

The final quality is almost entirely built in Phase 1: if the static image is consistent, the animation is just the cherry on top.

The final result: the looping animated infographic, generated with Gemini.

Phase 1: the image with nano banana

The trick is to use a reference image as a style sheet, not as a layout to copy. You tell the model to take only two things: the rendering style (Sticker Art Die-Cut, black and white, thick white borders) and the character's physique. Everything else (composition, actions, text) it reinvents for every new theme.

The operational steps:
  1. 1 Open a new chat on Gemini and make sure you're using the image model (nano banana).
  2. 2 Upload the reference image: the one you want to inherit the style and character physique from.
  3. 3 Paste the prompt below, filling in the final bracket with the text you want turned into an infographic.
  4. 4 Wait for the model to confirm, then ask for the first infographic. If the style holds up, keep going; otherwise repeat the critical instruction.

The part that makes the difference is the critical instruction about the image: it clearly separates "what to clone" from "what to ignore". Without this distinction, the model copies the reference layout and you lose the infographic.

Static infographic in black-and-white Sticker Art style generated with nano banana
The static infographic (Phase 1) in Sticker Art style, before the animation.

The base prompt to copy

Copy this template, attach the reference image and replace the final bracket with the text you want to turn into an infographic.

PROMPT: PHASE 1 (STYLE)
CRITICAL INSTRUCTION ABOUT THE ATTACHED IMAGE

Use the image I've given you EXCLUSIVELY as a "style sheet" and
"character reference". You must copy ONLY two things:

1. THE RENDERING STYLE: black-and-white Sticker Art Die-Cut, thick white
   borders, sharp black outlines, expressive comic-like look.
2. THE CHARACTER'S PHYSIQUE: young guy, short dark hair, neat dark beard,
   lively expression.

COMPLETELY IGNORE the layout, the composition, the character's actions
and any text or content present in the reference image.

ROLE: You are a Visual Designer specialized in narrative infographics in
B&W Sticker Art. You adapt the fixed character to new layouts and new
actions based on the theme I give you.

OPERATING RULES:
- Invent a layout structure suited to the topic.
- Have the bearded character perform different actions for each step.
- Keep the B&W Sticker Art aesthetic strict throughout the infographic.

Confirm you understand you must "clone" the character's look and graphic
style, but completely reset composition and actions with every new
request.

THEME TO TURN INTO AN INFOGRAPHIC:
[TEXT I WANT TO TURN INTO AN INFOGRAPHIC]

The parts in ALL CAPS in brackets are your inputs. If you change the graphic style (colors, linework), rewrite points 1 and 2 of the critical instruction: they're the only two levers that matter.

Phase 2: the animation with VEO

Open a new chat on Gemini, select VEO and upload the static image you just generated. The goal here is the opposite of "make everything move": you want looping micro-movements, only on the characters, with text and background still.

PROMPT: PHASE 2 (ANIMATION)
Your goal is to add very subtle looping animations
EXCLUSIVELY to the characters.

All other elements (text, background, icons) stay completely
static. No camera movement, no zoom.

The movement must be minimal and loop-repeatable: a breath, a
small gesture, a blink. The output is meant for a LinkedIn
post, so it has to catch attention without distracting from reading.

A minimal movement (a breath, a blink) is what stops the scroll on LinkedIn without making the post unreadable. If the video comes out too "alive", repeat the prompt insisting on exclusively to the characters.

Tips and limitations

The character doesn't stay 100% identical between generations: regenerate until the physique is consistent again before moving on to animation.
VEO tends to add movement even where it's not needed. If it animates text or background, repeat the prompt insisting on EXCLUSIVELY to the characters.
The export is a video: fine for LinkedIn, but for a static post convert it to a GIF or extract a frame as an image.

The workflow isn't magic: it's discipline. Style locked in Phase 1, minimal movement in Phase 2. If you respect the order and stay strict with the critical instruction, you get recognizable, consistent animated infographics: a format that's yours, not just any template.

From a Confusing Brief to a Complete UX/UI A vague brief becomes a navigable app. Product Ad From a Single Photo A photo becomes an animated ad, no code required. Get Claude to Watch Your Videos Claude watches your videos and turns them into text. Higgsfield Inside Claude Code Generate images and video while you code in Claude Code. Turn a Loom Recording Into a Web Page A screen recording becomes a web page, no code. Vertical Shorts With NotebookLM Your sources become a vertical short. Luxury Landing Pages on Lovable A luxury landing page from a single prompt. Excalidraw Running Locally Excalidraw free on your computer, no code. Mistral OCR in Your Workflow Extract text from documents with Mistral OCR. Claude SEO in the Terminal 25 free SEO skills inside Claude Code. Google Search Console inside Claude Code Search Console data inside your terminal. Claude Code Routines Claude working on its own, computer off. Clone a Landing Page in React With v0 Clone a real landing page into React code. Context Economy With Claude Work light and don't burn through Claude's limits. From Prompt to Self-Improving Skill Claude skills that learn from your mistakes. From NotebookLM to Canva: Presentations NotebookLM slides, finally editable in Canva. The Map for Understanding Every AI Tool 12 categories for placing any AI tool. Transparent PNGs With ChatGPT Real transparency, not a fake checkerboard. Animated Infographics With Gemini Infographics that loop, animated with Gemini. Market Research With Deep Research Deep Research as your market analyst. Get Cited by AI Search Engines (AEO) Become a source that ChatGPT and Perplexity cite.