Models

Nano Banana Prompts: 15 Examples for Thumbnails, Product Stills and Storyboards

Fuxuan Guo
37 min read
Nano Banana Prompts: 15 Examples for Thumbnails, Product Stills and Storyboards
Contents
  1. Key Takeaways
  2. How to write Nano Banana prompts
  3. Set up Nano Banana in ChatCut
  4. Plan the asset before the prompt
  5. Thumbnail prompts for YouTube and Shorts
  6. Product still prompts
  7. Storyboard frame prompts
  8. Character consistency prompts
  9. Prompts for text in images
  10. Revise without starting over
  11. When a Nano Banana image misses
  12. Put the stills to work in your edit

A Nano Banana prompt works best as a brief to a photographer: what the image is for, what each attached reference controls, what’s in the frame and where, the light, and what must stay exactly as it is, written in full sentences. This guide gives you 15 Nano Banana prompts for the stills a video needs: thumbnails, product stills, storyboard frames, a recurring character and images with readable words. Each card lists the inputs, the prompt, why it’s written that way and what to check before you use the result. Every prompt runs as written in ChatCut’s AI panel, where Nano Banana requires a paid plan and uses credits for each image.

Every card below shows the image we got when we ran its prompt as written in ChatCut on November 21, 2026: the first result each time, at 1K, with no retries. We used Nano Banana Pro for the cards where lettering decides the result (5, 13, 14, 15 and the headline edit) and Nano Banana 2.1 for the rest; the whole set cost about 5.7 credits. Cards with attached photos show the inputs on the left. Those are stock photos from Unsplash, plus, for the product cards, a stock photo of an unlabeled amber bottle with a label we designed for this test. Card 2 has no result, and the card says why. The one demo video on this page comes from a ChatCut Skill that runs on a different model, and it’s labeled that way.

Key Takeaways

  • Write a brief, not a list of tags: purpose, references with one job each, subject, composition, light, and what stays fixed.
  • Plan the empty space first. Decide where the headline, the player’s buttons or the title will sit, then describe the pose.
  • Keep real photos as your references. For a new framing, rerun the original prompt with a new shot sentence instead of feeding a generated image back in.
  • Words and labels are where stills fail most visibly. Quote the exact words, keep them short, and read every letter at full size. Words that must stay editable belong on the timeline, not in the pixels.

How to write Nano Banana prompts

Google’s image-generation guide gives the same core advice for all its Nano Banana models: be specific, explain what the image is for, use camera and lighting language to set the composition, and describe the scene you want instead of listing what to leave out. The Nano Banana Pro prompting guide from Google’s AI developer team frames it as briefing a creative director rather than typing keywords. For stills that go into a video, that advice turns into six parts.

The card 4 product-still prompt split into six colored parts: job and shape, references, subject, composition, light and look, and fixed details. A row for each part explains what it controls and why it matters for Nano Banana.
Six parts of a Nano Banana prompt, using card 4 from this guide. The order matters less than having each part once.
  1. Job and shape. Start with the model, the asset and its aspect ratio: “Use Nano Banana to make a 16:9 hero still for the opening shot of a product video.” The purpose changes choices you didn’t spell out. A thumbnail needs a face that reads at phone size; an opening shot needs room for a title.
  2. References. Give every attached image one job: “The attached photo is the product reference: keep its shape, cap and label exactly.” ChatCut’s generation references guide makes the same point: a reference without a stated role can be read in ways you didn’t intend.
  3. Subject. What’s in the frame, in plain nouns with two or three defining details. When a reference supplies the look, point at it instead of describing it again.
  4. Composition. Where things sit and what stays empty: “in the right third”, “keep the left two-thirds as plain wall”. Shot size and lens (“eye level, 85mm”) do more than adjectives like “cinematic”.
  5. Light and look. Direction and quality of light, plus the photographic style: “soft window light from the left”, “candid documentary photography”.
  6. Fixed details. What must not change, and what fills the areas you want clean. Google recommends describing what should be there (“a plain, unmarked wall”) rather than what shouldn’t. Keep a short exclusion only for the one thing that would ruin the asset, usually stray text.

Two habits from Google Cloud’s image-generation best practices carry over directly. Ask for an image in so many words, so the model doesn’t answer with text. And for complex scenes, write the parts in order: background, then subject, then the detail that matters most.

Set up Nano Banana in ChatCut

  1. Check your plan. ChatCut’s image models require a paid plan and enough credits, per the image generation guide.
  2. Open the AI panel in Agent mode. The steps below use the Agent. In ChatCut Desktop you can also switch to Image Gen, pick a Nano Banana model and paste the prompt; it makes one image per request.
  3. Add your references. Select + → Add files to attach files from your computer. To use something already in the project, turn on Selection Mode below the prompt field and select a clip, an asset in the Media Pool, a point on the Timeline ruler or a box in the Viewer. Each one appears as a chip in the prompt.
  4. Paste the prompt. Every card starts with “Use Nano Banana” because ChatCut’s default image model is GPT Image 2.6 Flare; without the name, you may get that instead. Ask for more than one image if you want options. ChatCut makes 1 to 10 per request, each as its own job.
  5. Allow the job. If a confirmation card appears, check the request and the credit estimate, then select Allow this time.
  6. Use the result. Follow progress in the conversation or the Media Pool. Drag the finished image onto a video track, or right-click its card and choose Export source (in ChatCut Desktop, Save a Copy…).

In ChatCut a 1K image costs about 0.2 credits on Nano Banana 2.1, 0.33 on Nano Banana 2 and 0.72 on Nano Banana Pro (quotes from November 15, 2026; the Nano Banana page compares the three versions). One credit has a face value of $0.25. Larger sizes cost more, and each image is a separate charge. Check the estimate on the confirmation card before you allow a job; Credit activity shows the final charge.

Google offers several Nano Banana models, including Nano Banana 2 and Nano Banana Pro, and its model list includes newer versions too. ChatCut has three of them: Nano Banana Pro, and Nano Banana 2.1 and 2. The cards below are plain-language briefs of the kind Google recommends for all of them, so they carry over if you use another version elsewhere. The setup, prices and limits on this page are ChatCut’s.

When to switch models. Two differences are fixed. A transparent background (a PNG cutout) needs GPT Image 2.5 or later, or Seedream 5.5; Nano Banana in ChatCut doesn’t offer it. And for cheap drafts, GPT Image 2.5 starts at 0.02 credits per image at low quality. For how the two model families compare on realism, text and layout, see GPT Image 2 vs Nano Banana Pro. The prompts in this guide run on either; only the model name changes.

Plan the asset before the prompt

Every still in a video has a shape it must fit, an area that must stay clear and one detail that decides whether it’s usable. Settle those three things first; most of the prompt follows from them.

Six asset types as cards: YouTube thumbnail, Shorts cover, product still, storyboard frame, character scene and text card. Each lists its shape, its references, the area to keep clear and what to check before using it.
What each kind of still needs before you write the prompt. Shapes for YouTube from its thumbnail help page; everything else follows the cards below.

Thumbnail prompts for YouTube and Shorts

A thumbnail has to work at the size of a phone search result, so it carries one face, one object and a few words at most. YouTube’s thumbnail requirements ask for 16:9 for videos and 9:16 for Shorts, at least 640 pixels on each side. Our YouTube editing guide covers the rest of the upload rules.

Decide the layout before the pose: where the headline goes, then where the face and the product sit. These cards leave the words out of the first version. When the headline is generated together with the face and the product, a misspelled word and a drifted face both cost a full regeneration. Approve the picture first, then add the words with a follow-up edit (see Revise without starting over) or in your design tool.

1. Presenter and product from a real frame

Inputs: a frame of your video where the presenter faces the camera (Selection Mode, then click that point on the Timeline ruler) · a clean photo of the product, attached with + · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 YouTube thumbnail. The frame I selected is the reference for the presenter: keep their face, hair and clothing as they appear in it. The attached photo is the reference for the headphones: keep their shape, color and logo position. Show the presenter from the chest up in the left half of the frame, looking into the camera with a small, confident smile, holding the headphones up beside their face. Bright, soft light from the front and a smooth warm-gray background. Keep the right third of the frame as plain background for a headline added later.
Inputs on the left: a stock photo of a smiling man in a plaid shirt and a product photo of black over-ear headphones. Result: a 16:9 thumbnail of the same man from the chest up on the left, holding the headphones beside his face, with the right third left as plain gray wall.
Card 1 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The face, the plaid shirt and the headphones match the two photos, and the right third stayed empty. The background came out a cooler gray than the warm gray we asked for.

Why it’s written this way: a frame from the video itself keeps the thumbnail honest; viewers notice when the person on the cover isn’t the one in the video. The expression change is kept small, because a new expression is where a face most often stops looking like its reference.

Check: compare the face with the frame at full size, then shrink the image to the width of a phone search result. If the face drifts, drop the expression clause and write “keep their expression from the frame”.

2. Before and after in one frame

Inputs: two photos of the same desk, before and after, taken from the same spot and attached in that order · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 before-and-after thumbnail from the two attached photos of the same desk. Split the frame down the middle with a thin white vertical line. Left half: the desk from the first photo, cluttered, in slightly cool, flat light. Right half: the desk from the second photo, tidy, in warm, bright light. Match the camera angle and the desk position on both sides so only the change stands out. Show only objects that appear in the photos, and keep both halves free of words and arrows.

What we got: Nothing to show for this one. It needs two real photos of the same desk taken from the same spot, before and after, and we didn’t have a pair we could publish. Making the “after” photo with AI would defeat the point of the card.

Why it’s written this way: the split is the message, so everything else is held equal. The difference is pushed with light and color, not with new objects, which keeps the promise of the thumbnail true to the video.

Check: nothing on the right side that isn’t in your after photo. If the model tidies further than you did, add “The right half reproduces the second photo; only the light changes.”

3. A vertical cover, recomposed

Inputs: the same frame and product photo as card 1 (not the card 1 result) · 9:16

Try this promptOpen in ChatCut
Use Nano Banana to make a 9:16 cover for the YouTube Short of the same review. The frame I selected is the reference for the presenter and the attached photo is the reference for the headphones; keep both exactly as they appear there. Compose for a vertical screen: the presenter from the waist up in the center of the frame, holding the headphones at chest height, against the same smooth warm-gray background with soft light from the front. Keep the top fifth and the bottom quarter of the frame as plain background, where on-screen titles and buttons usually sit.
Inputs on the left: the same presenter and headphones photos as card 1. Result: a 9:16 cover of the man from the waist up in the center, holding the headphones at chest height, with plain space above and below.
Card 3 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: Same person, shirt and headphones as card 1, recomposed for a vertical screen rather than cropped, with clear space at the top and bottom.

Why it’s written this way: a vertical cover is a new composition, not a crop of the wide one. Cropping a 16:9 image to 9:16 throws away about two-thirds of it, often including the product. Reusing the real references and the same light sentence keeps the pair consistent without passing a generated image back through the model.

Check: set the two covers side by side. Same person, same product, same palette; the face and product clear of the top and bottom edges.

Product still prompts

A product video needs a handful of stills that cut together: a hero for the opening, a close-up of the detail buyers check, and the product in use. Cards 4 to 6 use one product, a glass bottle of cold brew coffee, so you can see how the sentences repeat. Start from a sharp, front-facing photo of your product on a plain background with the label in focus. The model can only keep what it can see.

4. Hero still with room for a title

Inputs: a sharp front photo of the product, attached with + · 16:9, or 9:16 for a vertical edit

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 hero still for the opening shot of a product video. The attached photo is the product reference: keep the bottle's shape, cap, label layout, colors and printed text exactly as they are. Stand the bottle upright on a pale travertine plinth in the right third of the frame, label facing the camera. Soft window light from the left with a long, gentle shadow falling to the right, and a warm off-white wall behind. Realistic commercial product photography at eye level with an 85mm lens. Keep the left two-thirds of the frame as clean, softly lit wall for a title added in the edit.
Input on the left: an amber bottle with a cream Lumen Roast Cold Brew label. Result: the bottle standing on a pale travertine plinth in the right third, with a soft-lit off-white wall filling the left two-thirds.
Card 4 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The label’s wording, typeface and layout survived, and the left two-thirds is clean wall. The shadow is shorter and softer than the long one the prompt asks for.

Why it’s written this way: the purpose (“opening shot of a product video”) and the reserved space work together. The empty two-thirds is described as what it is, a softly lit wall, so the model has something to draw there besides props.

Check: the shape, cap and label against your product photo. If the bottle comes out too small or too large on the plinth, give a height: “about 20 cm tall”.

5. Label close-up for an insert shot

Inputs: the same product photo as card 4 · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 close-up insert for the same product video. The attached photo is the product reference: keep the label's wording, typeface, logo and colors exactly as printed. The label fills about two-thirds of the frame, seen straight on at label height, with the bottle's glass shoulder at the top and the edge of a pale travertine plinth at the bottom. Soft window light from the left and a warm off-white wall behind, softly out of focus. Macro product photography, shallow depth of field, the label in crisp focus.
Input on the left: the labeled amber bottle. Result: a close-up of the label filling most of the frame on the edge of a travertine plinth, every line of text sharp.
Card 5 result, generated with Nano Banana Pro in ChatCut on November 21, 2026.

What we got: Every word on the label reads the same as the photo, including the small italic line and “330 ml · ready to drink”. We ran this card on Nano Banana Pro because one wrong letter would sink the shot.

Why it’s written this way: the set and light sentences are copied from card 4, so the close-up cuts against the hero. The reference is your real photo, not the generated hero, so the label is copied from the product rather than from a copy of it.

Check: zoom to 100% and read every word against the real bottle. If one letter changes, don’t use the image: a close-up shows a wrong label to every viewer. Retake the reference sharper and straight on, or film the real label for this shot.

6. The product in use, for B-roll

Inputs: the same product photo · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 lifestyle still of the bottle in the attached product photo, for B-roll under a voiceover. An adult's hand pours the cold brew from the bottle into a glass of ice on a kitchen counter, with morning light from a window on the right. The bottle is in sharp focus left of center with its label toward the camera; the glass and the kitchen behind are softly blurred. Keep the bottle's shape, cap, label and colors exactly as in the photo, at a real size for the hand: about 20 cm tall. Candid documentary photography, natural colors.
Input on the left: the labeled amber bottle. Result: a hand pouring cold brew from the bottle into a glass of ice on a kitchen counter, morning light from a window on the right.
Card 6 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The hand has five fingers, the pour lands in the glass and the label is still correct even though the bottle is tilted. The bottle sits closer to the center than the prompt’s “left of center”.

Why it’s written this way: B-roll sits next to filmed footage, so the style asks for candid photography rather than a studio look. The size is given in centimeters because scale is the detail composites most often get wrong.

Check: the hand (count the fingers), the pour and the label direction. If the hand looks wrong, give it a simpler job, such as holding the bottle upright by its neck instead of pouring.

If you’d rather pick a ready-made scene than write the brief, ChatCut’s Product Photos Skills do this job from one product photo: studio sets, real places, in-hand shots, flat lays and more. They run on GPT Image 2.5 rather than Nano Banana, and you choose the scene from examples instead of describing it.

Storyboard frame prompts

Storyboard frames let you test a sequence before you shoot or generate it, and a good frame can become the first frame of a generated clip. What makes three frames read as one scene is continuity: the same person in the same clothes, the same room, light from the same side, and the camera staying on one side of the action.

The way to get that is a master description you paste into every frame’s prompt word for word. Only the shot sentence changes. Generate one frame per request, so a bad frame can be redone without touching the others, and attach the same two real photos every time rather than the previous frame.

A master description of the presenter, the room and the light, pasted unchanged into three storyboard prompts. Below it, three sketched 16:9 frames: a wide shot from the doorway, a medium shot of her opening a laptop and a close-up of her hand on the trackpad, each with its one changing shot sentence and the window light marked on the left.
Three frames, one master description. Only the shot sentence changes; the window stays on the left and the camera stays on one side of her.

7. Wide establishing frame

Inputs: a photo of the presenter, who has agreed to it · a photo of the room · both attached with +, in that order · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make storyboard frame 1 of 3. The first attached photo is the presenter: keep her face, short dark hair and rust-colored sweater. The second attached photo is the room: keep the oak desk, the bookshelf on the right and the tall window on the left. Late-afternoon sunlight comes through the window from the left of the frame. Photographic storyboard frame, 16:9, natural colors. Shot: a wide shot from the doorway at standing eye level. She sits at the desk in the middle of the frame, facing a closed laptop, with the window on the left and the bookshelf on the right.
Inputs on the left: a photo of a woman with short dark hair in a rust-orange sweater, and a photo of an attic study with a window, a wooden desk and a bookshelf. Result: a wide shot from a doorway of her at the desk with the window on the left and the bookshelf on the right.
Card 7 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The room is recognizably the one in the photo, with the window left and the shelf right. The model also wrote a small “1 of 3” in the corner, taken from “frame 1 of 3” in the prompt; crop it or add “no captions” if you don’t want it.

Why it’s written this way: the first four sentences are the master description. The wide frame establishes the geography every later frame must respect: window left, shelf right, desk in between.

Check: the room matches your photo closely enough that a viewer would accept it as the same place.

8. Medium action frame

Inputs: the same two photos, in the same order · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make storyboard frame 2 of 3. The first attached photo is the presenter: keep her face, short dark hair and rust-colored sweater. The second attached photo is the room: keep the oak desk, the bookshelf on the right and the tall window on the left. Late-afternoon sunlight comes through the window from the left of the frame. Photographic storyboard frame, 16:9, natural colors. Shot: a medium shot from the right side of the desk at seated eye level. She opens the laptop with both hands and looks at the screen, which faces away from the camera. The window stays at the left edge of the frame.
Inputs on the left: the same presenter and room photos. Result: a medium shot of the woman opening a laptop at the wooden desk, the window at the left edge of the frame.
Card 8 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: Sweater, hair and light direction match frame 1, and the window stayed on the left.

Why it’s written this way: one action, and a sentence that pins the window to the left. If the light or the window jumps sides between frames, the cut reads as a different room or a different time of day.

Check: sweater color, hair and the light direction against frame 1.

9. Detail insert

Inputs: the same two photos, in the same order · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make storyboard frame 3 of 3. The first attached photo is the presenter: keep her face, short dark hair and rust-colored sweater. The second attached photo is the room: keep the oak desk, the bookshelf on the right and the tall window on the left. Late-afternoon sunlight comes through the window from the left of the frame. Photographic storyboard frame, 16:9, natural colors. Shot: a close-up of her right hand on the laptop's trackpad, the cuff of the rust-colored sweater at the edge of the frame, the screen softly out of focus, sunlight falling from the left.
Inputs on the left: the same presenter and room photos. Result: a close-up of a hand on a laptop trackpad with a rust-orange sleeve at the edge of the frame and the screen out of focus.
Card 9 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The cuff color matches frames 1 and 2 and the hand holds up at full size. Light falls from the left, as written.

Why it’s written this way: an insert shows almost nothing of the person, so continuity rides on two details: the sleeve color and the light direction. Both are named.

Check: the cuff color matches frames 1 and 2, and the hand is plausible at full size.

Drop the three frames onto the timeline at two or three seconds each and play them: you’ll see straight away whether the sequence reads. To fill a gap in an existing edit, select that point on the Timeline ruler with Selection Mode and add “for the gap at the selected time, matching the shape of the surrounding clips” to the prompt. When a frame is approved, it can become the First Frame of a generated clip; our image-to-video prompts cover what to write for the motion.

Character consistency prompts

A recurring character, such as a channel host, a mascot or a person in a short story, has to be recognizable from scene to scene. Google documents up to 14 reference images for Nano Banana Pro, but more references aren’t the fix. One clean anchor image, attached every time, does more than a pile of scenes.

If the character is a real person, start from real photos of them, taken with their agreement, and attach those every time. If the character is invented, card 10 makes the anchor. In both cases, never use the latest scene as the reference for the next one. Each pass redraws the whole image, so a small drift in scene 3 becomes the starting point for scene 4.

10. Create the anchor image

Inputs: text only · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 character reference image: the same woman shown three times side by side, in front view, three-quarter view and profile, standing, full body, on a plain light-gray background with even studio light. She is in her early thirties, with a round face, freckles and shoulder-length curly red hair, wearing a mustard-yellow raincoat over a navy sweater, dark jeans and white sneakers. Relaxed, neutral expression. Photographic, natural skin texture.
A 16:9 character sheet of one woman with curly red hair, a mustard-yellow raincoat over a navy sweater, dark jeans and white sneakers, shown in front, three-quarter and profile views on a light-gray background.
Card 10 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: All three views show the same person with the same clothes. We used this first result as the anchor for cards 11 and 12.

Why it’s written this way: three angles in one image give later prompts more of the character to work from, and the plain background keeps the reference about the person. Save this exact description; you’ll paste it into every scene.

Check: all three figures are the same person with the same clothing details. Regenerate until they are; everything after this inherits the anchor’s flaws.

11. Same character, new setting

Inputs: the approved anchor image (Selection Mode, then select it in the Media Pool) · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to place the woman from the attached reference image in a new scene, 16:9. Keep her face, freckles, curly red hair and the mustard-yellow raincoat over the navy sweater exactly as in the reference. Medium shot: she stands at a rainy bus stop at dusk, holding a paper cup of coffee, looking down the street to the right with a small smile. Wet pavement reflects the shop lights, with cool light from the street and warm light from inside the shelter. The shop signs in the background are blurred and unreadable. Change only her pose, the setting and the light.
Input on the left: the card 10 character sheet. Result: the same red-haired woman in the mustard raincoat at a rainy bus stop at dusk, holding a paper cup and looking down the street.
Card 11 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: Hair, raincoat and sweater carried over from the anchor; at this size the freckles are hard to see and she reads a few years older. A couple of shop signs in the background still show letter-like shapes.

Why it’s written this way: the last sentence draws the line between what’s allowed to change and what isn’t. The blurred signs are written as what they look like, which keeps invented lettering out of the background.

Check: eyes, nose, hairline and freckles against the anchor, then the raincoat’s color and collar.

12. Same character, close-up reaction

Inputs: the same anchor image · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 close-up of the woman in the attached reference image, for a reaction shot. Keep her face, freckles, curly red hair, the mustard-yellow raincoat and the navy sweater exactly as in the reference. Three-quarter view from her left, head and shoulders, inside a bright cafe: she reads a paper map with a slight frown of concentration. Soft daylight from a window behind the camera; the cafe is softly blurred behind her.
Input on the left: the card 10 character sheet. Result: a head-and-shoulders close-up of the same woman in a bright cafe, reading a paper map with a slight frown.
Card 12 result, generated with Nano Banana 2.1 in ChatCut on November 21, 2026.

What we got: The face holds up at close-up size next to the anchor, and the expression stayed small, as the prompt asks.

Why it’s written this way: a close-up magnifies every difference in the face, so the expression is a small one. Big expressions, such as a wide-open mouth or raised eyebrows, change the shape of the face the model is trying to keep.

Check: put the close-up next to the anchor at the same size. If she looks like a relative rather than the same person, shorten the list of changes and generate again from the anchor.

Prompts for text in images

Nano Banana can render short, legible text, and Google’s guide recommends deciding the exact words before you ask for the image. Three rules make it dependable: put the exact words in quotes, keep them to a few words, and say what the letters look like and where they sit. Then read every letter at full size. Words that must stay editable, be translated or animate belong on the timeline instead, as a Motion Graphics title or callout.

13. Chapter title card

Inputs: text only · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 chapter card for a cooking video. In the center, the words 'PART 2: THE SAUCE' in large, bold, cream-colored condensed sans-serif capitals, on a deep tomato-red background with a subtle paper texture. Below the title, a small hand-drawn illustration of a saucepan in the same cream color. The card holds nothing else.
A 16:9 tomato-red card with the words PART 2: THE SAUCE in cream condensed capitals and a small hand-drawn saucepan below.
Card 13 result, generated with Nano Banana Pro in ChatCut on November 21, 2026.

What we got: Spelled correctly on the first try, with nothing else on the card.

Why it’s written this way: four words, one typeface described by its look, and high contrast. A sparse card leaves the model nothing else to get wrong.

Check: spelling, letter by letter. If it keeps breaking, generate the background and the saucepan without the words, then add the title as a Motion Graphic on top.

14. Headline behind the subject

Inputs: a photo of the presenter, attached with + · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 thumbnail from the attached photo of the presenter. Across the top half of the frame, the word 'FOCUS' in huge, heavy black sans-serif capitals on a flat lemon-yellow background. She stands in front of the word, shown from the waist up in the center, covering only the lower part of the middle letters so the whole word still reads at a glance. Keep her face, hair and clothing as in the photo, with a calm, confident expression. Bright, even studio light.
Input on the left: a stock photo of a woman with curly auburn hair in a red sweater. Result: the same woman from the waist up in front of the huge black word FOCUS on a lemon-yellow background.
Card 14 result, generated with Nano Banana Pro in ChatCut on November 21, 2026.

What we got: Her face and sweater match the photo and the word still reads at thumbnail size, but her hair covers more of the C than “only the lower part”. If that bothers you, ask for her to stand a little lower in the frame.

Why it’s written this way: text layered behind a person is a common thumbnail style that’s tedious to cut out by hand. The prompt states how much of the word she may cover, because a headline hidden behind a head stops being a headline.

Check: the word reads in under a second at phone size, and her face matches the photo.

15. Labeled diagram for an explainer

Inputs: text only · 16:9

Try this promptOpen in ChatCut
Use Nano Banana to make a 16:9 explainer still for a coffee tutorial: a clean flat illustration of a pour-over setup on a white background, seen from the side. Four thin leader lines point to the parts, each ending in a label in dark gray sans-serif capitals: 'KETTLE', 'DRIPPER', 'PAPER FILTER' and 'CARAFE'. Use a muted palette of warm browns and soft blue, with generous white space around the drawing and the labels.
A flat 16:9 illustration of a pour-over setup with four leader lines labeled KETTLE, DRIPPER, PAPER FILTER and CARAFE.
Card 15 result, generated with Nano Banana Pro in ChatCut on November 21, 2026.

What we got: All four labels are spelled correctly and point to the right parts. The model put the labels in white on dark-gray tags instead of plain dark-gray type.

Why it’s written this way: a flat illustration on white keeps the labels the clearest thing in the frame. Four labels is a manageable number to check.

Check: each label points to the right part, and every word is spelled correctly. If a label lands on the wrong part, generate the drawing without labels and add them as Motion Graphics callouts, where you can also animate them in one at a time.

Revise without starting over

When an image is mostly right, ask for the specific change instead of generating a new one; Google’s prompting guide makes the same recommendation. In ChatCut, select the result in the Media Pool with Selection Mode so it’s attached, say what changes, and say what stays.

Try this promptOpen in ChatCut
Use Nano Banana to edit the attached image: make the light slightly warmer and remove the mug at the right edge of the counter. Keep everything else exactly as it is: the bottle, its label, the framing and the shadows.

This is also the safer way to add a headline to an approved thumbnail, since the face and product are already settled:

Try this promptOpen in ChatCut
Use Nano Banana to edit the attached thumbnail: in the empty right third, add the words 'TWO WEEKS LATER' in heavy white sans-serif capitals with a thin black outline, on two lines, large enough to fill most of that third. Change nothing else in the image.
Input on the left: the card 1 thumbnail. Result: the same thumbnail with TWO WEEKS LATER added on two lines in heavy white capitals with a thin black outline in the right third.
The headline edit run on the card 1 result with Nano Banana Pro in ChatCut on November 21, 2026.

The words came out spelled correctly in the empty third. The framing shifted slightly: the presenter sits a little larger than in card 1, so compare the two before you replace the original.

Each edit creates a new asset; the original stays in the Media Pool. Small edits like these are fine. For a new framing, a new angle or a new scene, go back to the original prompt and the real references and change the shot sentence, as in cards 7 to 9. Editing a generated image into a different shot asks the model to invent the parts it can’t see, starting from parts it already invented.

When a Nano Banana image misses

Generating the same prompt again mostly gets you another version of the same problem. Find the instruction that controls it and change only that.

  • The face changes. Fewer changes in one prompt and a smaller expression. Attach the real photo or the anchor again, never the last scene.
  • The label or logo is wrong. Use a sharper, straight-on product photo, keep the label facing the camera, and avoid close-ups until the wide shot is right. If it still changes, use a real photo for that shot.
  • Stray text appears on signs and screens. Describe those surfaces as what they look like: “blurred and unreadable”, “plain”, “a blank screen”. Then add one sentence saying the image contains no other words.
  • The empty space gets filled. Name the region and what’s in it: “the left two-thirds is plain, softly lit wall.”
  • The product is the wrong size. Give a real measurement and something to compare it with, such as a hand or a glass.
  • The vertical version loses the subject. Recompose for 9:16 in the prompt instead of cropping the 16:9 image.
  • It looks too smooth or artificial. Ask for a lens, a type of photography and “natural skin texture”. Replace tag strings like “8k, hyper-detailed” with a sentence describing the photograph.
  • The request is refused. Read the message. Use photos of real people only with their permission, and expect some subjects to be blocked by the model provider.

Put the stills to work in your edit

A generated image is a project asset like any other. Drag it from the Media Pool to a video track, then set its position, scale, crop and duration in the Inspector. If the image already exists on your computer, import it with Media Pool → Import → Files… (on the web, Upload → Files…) rather than generating it again.

From there, four things are common:

  • Titles on top. Put headlines and lower thirds over a still as Motion Graphics, so the words stay editable.
  • A cutout. Nano Banana doesn’t output transparent PNGs in ChatCut, but Seedream 5.5 does; the Seedream 5.5 prompt list starts with five sticker and cutout prompts. On ChatCut Desktop, Object Cutout in the Inspector can select an object in an image so you can place it over other footage.
  • Motion. Use an approved still as the First Frame in Video Gen to turn it into a clip.
  • A full product video. Product images are what ChatCut’s product-ad Skills start from. The demo below shows the kind of sequence a beverage ad builds: macro fruit, falling slices, a label close-up and a bottle hero.
Demo
An orange macro, falling slices, a label close-up and a bottle hero shot. From the Citrus Storm Skill, which generates with Seedance, not Nano Banana.

The Citrus Storm Skill turns product images, flavor details and brand information into a beverage commercial like this one. The label close-up in its sequence is the shot to check most carefully, for the same reason as card 5.

Generate the stills with Nano Banana and cut them into your video on the same timeline.Download DesktopDownload for macOSDownload for WindowsDownload ChatCut Desktop

Questions about Nano Banana prompts

What makes a good Nano Banana prompt?
A brief in full sentences: what the image is for, what each reference controls, what's in the frame and where, the light, and what must not change. Describe the areas you want empty as what they look like, such as 'a plain, softly lit wall', rather than listing what to leave out.
Do I always need reference images?
No. Text alone works for new scenes, title cards and invented characters. Attach references when something must stay recognizable, such as a person, a product or a room, and give each one a single job in the prompt.
What are good image prompts for Gemini?
Image generation in Gemini runs on Google's Nano Banana models, so the same advice applies: state the purpose and the aspect ratio, describe the scene in full sentences, and use camera and lighting language. Any card in this guide is a starting point; change the subject and keep the structure.
Do these prompts work with Nano Banana Pro and Nano Banana 2?
They're plain-language briefs of the kind Google recommends for all its Nano Banana models, so they carry over. ChatCut's image models include one called Nano Banana; the setup, prices and limits in this guide are ChatCut's.
Can Nano Banana put readable text in an image?
Often, for short phrases. Put the exact words in quotes, keep them to a few words, describe the lettering and where it sits, and check every letter at full size. Words that must stay editable work better as a title on the timeline.
Is Nano Banana free in ChatCut?
The prompts are free to copy. Generating requires a paid plan and uses credits; each image is a separate charge, and the confirmation card shows the estimate.

Checking your footage...

Less editing. More creating.

Download ChatCut Desktop free and make your first video today.

Download Desktop Download for macOS Download for Windows Try it for free