Veo & FlowConsistent charactersImage-to-video

Flow Ingredients and Scenebuilder: Consistent Characters

By Marco Cavazzana · Updated · 5 min read
ShareEmail
Short answer

In Google Flow, consistency comes from two tools working together. Ingredients to Video lets you upload reference images of a character, object or style and reuse them in every shot, Extend continues an 8-second Veo clip, and Scenebuilder arranges and trims your clips into a sequence. Build clean reference images first, describe the character the same way in every prompt, and extend rather than regenerate whenever you can.

A single good clip is easy. A sequence where the same person, wearing the same coat, walks through the same street in five different shots is the real test of a video tool. Google Flow answers it with Ingredients to Video and Scenebuilder. This guide shows how to prepare references, prompt with them, and chain shots into a sequence. Flow is updated frequently, so some labels may have shifted since this was written; the method holds.

Prepare ingredients worth reusing

An ingredient is a reference image Flow uses as a visual anchor. The quality of the result follows the quality of the reference, so spend time here before spending credits.

  • Character references: a clear front-facing image, well lit, plain background, the full outfit visible. Add a three-quarter view if you can. Avoid strong shadows, sunglasses and hats unless they are part of the character.
  • Object and product references: the item alone on a neutral background, sharp, no reflections of other objects. Two angles help.
  • Style references: a frame that shows the palette, grain and lighting you want, without a strong subject that could leak into the shot.
  • Keep a small set. Two or three ingredients per shot is manageable; more and the model has to guess which matters.

Flow’s image tools are a quick way to produce clean character sheets and variations. Images from any other tool work too, and the general advice in consistent characters about fixing hair, outfit and distinguishing features applies here as well.

Prompting with Ingredients to Video

Switch the mode to Ingredients to Video, upload your references, and write a prompt that tells Flow how the ingredients come together. The images supply appearance; the prompt supplies everything they cannot show.

  1. Refer to each ingredient by a short, fixed description. "The woman in the yellow raincoat" and "the blue enamel kettle", worded identically in every prompt in the project.
  2. Describe the action and setting as you would in a text prompt: one action, one camera move, light, and a sound sentence.
  3. Do not re-describe what the reference shows. Repeating hair colour and outfit can conflict with the image and cause drift. Mention only what the reference cannot tell the model, such as expression or pose.
  4. Keep the style ingredient constant. The same look reference in every shot is what makes a sequence feel like one film.

Generate two outputs for character shots, because likeness varies between them, and pick the one that matches best before you build on it.

Frames to Video for exact starts and ends

When you need a precise opening frame, for example a product in an exact position, Frames to Video is more dependable than ingredients. Upload a start frame, optionally an end frame, and describe only the motion between them. A start frame generated with your character ingredients in Flow or another image tool gives you both exact composition and a consistent face.

Start and end frames should share a camera position and light. Big differences between them force the model to invent a transition, and that is where faces and objects distort. If you need a big change, use two clips and a cut.

Extend, then build the scene

Two tools turn single clips into a sequence: Extend, which continues one shot, and Scenebuilder, which arranges shots.

  • Extend continues the shot for a few more seconds from where it ended. The prompt for an extension should describe what happens next, not re-describe the scene. "She turns and walks towards the shop door" is enough. Each extension is a new generation, so expect small drift over several extensions; three or four is a practical limit before you cut.
  • New shots of the same scene are separate generations with the same ingredients: "close-up of her hand on the door handle", "wide shot from across the street". You can also save a frame of a clip (pause, hover, Save frame) and use it as the start frame of the next shot. Add the clips to Scenebuilder with More, then Add to Scene, where you drag them into order, trim each end and preview the sequence.

Two current limits matter for planning. Extend works only on 8-second Veo 3.1 clips and is generated with Veo 3.1 Lite. Ingredients work with Veo 3.1 Lite and Fast at 8 seconds, and with Gemini Omni Flash at any length, but not with Veo 3.1 Quality. Gemini Omni Flash also lets you add a voice reference to keep a character's voice across clips.

Settings at a glance

SettingWhat it doesStart with
ModeIngredients to Video for reusable references; Frames to Video for an exact first frameIngredients for characters, Frames for products
IngredientsReference images of characters, objects or style used in the shot1 character, 1 object, 1 style at most
Start and end frameFixed first and optional last image of the clipStart frame only, until you need a precise ending
ExtendContinues a clip for a few more secondsDescribe only the next action
ScenebuilderArranges, trims and previews clips as a sequenceAdd each approved clip as you go
Outputs per promptNumber of clips from one prompt2 for any shot showing a face

Keeping a sequence coherent

Even with good tools, a few habits make the difference between a film and a collection of clips. Write a one-line character description and a one-line style description at the top of your project notes, and paste them into every prompt unchanged. Light the whole sequence the same way; a change from dusk to noon between shots is more jarring than a slightly different face. Review the sequence in order after every two or three clips, because drift shows across a cut. Save the ingredient images with the project files, since a prompt without its references cannot be rerun. For the basics of the interface and credits, see Google Flow and Veo 3: getting started.

Try it

Ingredients: [front-facing character reference], [three-quarter character reference], [style frame: cool blue dusk, light rain, 35mm film grain].
Prompt: The woman in the yellow raincoat stands under a bus shelter and checks her watch. Medium shot, camera static, shallow depth of field. Cool blue dusk, light rain, 35mm film grain. Sound: rain on the shelter roof, a distant engine, no music.
Extend: She looks up as headlights approach and steps towards the kerb.
Next shot (same ingredients): Close-up of her face lit by the approaching headlights, rain on her hood.

Run the first prompt, choose the better of two outputs, extend it with the Extend line, generate the close-up as a new shot with the same ingredients, and arrange both in Scenebuilder. Change the setting sentence for a second scene but leave the character and style wording untouched, and compare how well her face holds across the two locations.

Frequently asked questions

How do I keep the same character across Google Flow videos?
Use Ingredients to Video with one or two clean reference images of the character, refer to them with the same short description in every prompt, extend 8-second Veo clips where a shot should continue, and generate further shots with the same ingredients before arranging them in Scenebuilder. Keep the lighting and style reference the same across the sequence.
What is the difference between Ingredients to Video and Frames to Video in Flow?
Ingredients to Video takes reference images of characters, objects or styles and combines them into a new shot you describe. Frames to Video uses an exact image as the first frame, and optionally another as the last, so it is better when composition must be precise.
How many times can I extend a clip in Scenebuilder?
Each extension is a new generation that continues from the previous one, so small drift accumulates. Three or four extensions is a practical limit for faces before you cut to a new shot. Extend currently works on 8-second Veo 3.1 clips and is generated with Veo 3.1 Lite.

Nothing you makeis lost.

Free · No card · Read-only · 2-minute setup

DreamdriveFree plan · Chrome
Add to Chrome — it’s free