demobook

OpenArt: Multi-subject consistency in movie posters

Demo summary

The video shows the process of dropping 14 different reference images into OpenArt and using Nano Banana 2 to combine them into a single, consistent animated movie poster.

Step-by-step

  1. Drop all reference images into OpenArt.
  2. Type a description of the desired output, such as an official animated movie poster.
  3. Describe specific characters or objects from the uploaded images.
  4. Tag the specific images you are describing to help the AI identify characters and objects.
  5. Turn on the Auto Polish feature for long prompts to enhance the text.
  6. Click Generate.

Options

  • Tag specific images to help the AI understand character/object placement

Tips

  • Use Auto Polish for longer prompts to get a more enhanced result.
  • Describe each subject in detail (e.g., 'young Asian girl with dark hair') to ensure consistency.

All demos from “How To Use Nano Banana 2 Better Than 99% of People

  1. 1:320:44Generate historical image grids with Nano Banana 2The creator demonstrates how to use Nano Banana 2 in OpenArt to generate a 2x2 grid of the Roman Coliseum across different historical eras using specific coordinates and time-based prompts.OpenArtText to Image
  2. 4:300:32Create hyperrealistic celebrity portraitsThe user demonstrates generating a high-detail cinematic portrait of Margot Robbie using Nano Banana 2 on OpenArt, bypassing standard Gemini restrictions.OpenArtAI Realistic Image Generator
  3. 5:571:20Render complex text and reflections in imagesA demonstration of Nano Banana 2's ability to render multiple specific text elements simultaneously, including a boarding pass, code on a laptop, and a mirrored neon sign.OpenArtAI Realistic Image Generator
  4. 10:200:55Multi-subject consistency in movie postersCurrentThe video shows the process of dropping 14 different reference images into OpenArt and using Nano Banana 2 to combine them into a single, consistent animated movie poster.OpenArtAI Image Combiner
  5. 11:521:16Generate instructional infographics from photosThe user demonstrates how Nano Banana 2 can analyze a photo of a car and recreate it as a 1970s-style instructional infographic detailing camera settings and lighting positions.OpenArtImage to Image
  6. Watch “How To Use Nano Banana 2 Better Than 99% of People” →

AI Image Combiner

  1. 14:271:32Place character in a real-world photoThe creator demonstrates the 'place character in image' feature to insert the AI influencer into an uploaded photo of a luxury retail store.Roboverse
  2. 10:200:55Multi-subject consistency in movie postersCurrentThe video shows the process of dropping 14 different reference images into OpenArt and using Nano Banana 2 to combine them into a single, consistent animated movie poster.Dan Kieft
  3. 9:020:58Combine character and background referencesThe tutorial shows how to use the Nano Banana model to composite a character reference into a specific background image.AI Video School
  4. 4:070:20Compose a scene using saved library assetsThe user tags multiple saved assets (character, prop, environment, style) in the reference panel to generate a fully consistent composite image.Roboverse
  5. 5:310:43Consistent objects and backgroundsA walkthrough of saving specific objects and backgrounds to a library and then combining them with a saved character to generate a consistent scene.Isa does AI