demobook

Generate AI image from PDF prompt in OpenArt

Demo summary

The creator demonstrates how to upload a PDF to ChatGPT to extract a prompt and then pastes it into OpenArt using the Nano Banana Pro model to generate a 4K image of a person on the moon.

Step-by-step

  1. Download your source material as a PDF
  2. Upload the PDF to ChatGPT and ask it to generate an image prompt based on the content
  3. Request ChatGPT to summarize the output into a single concise prompt
  4. Copy the prompt and navigate to the Create Image section in OpenArt
  5. Select the Nano Banana Pro model
  6. Paste the prompt into the input field
  7. Set the aspect ratio to 16x9 and resolution to 4K
  8. Select the number of images to generate and click create

Options

  • Adjust the number of images generated to increase selection variety
  • Choose different output resolutions up to 4K

Tips

  • Generate four images at once so you have more options to choose from

All demos from “How to Start Making AI Videos in 2026

  1. 5:060:57Generate AI image from PDF prompt in OpenArtCurrentThe creator demonstrates how to upload a PDF to ChatGPT to extract a prompt and then pastes it into OpenArt using the Nano Banana Pro model to generate a 4K image of a person on the moon.OpenArtText to Image
  2. 8:291:01Image-to-image generation with Seedream 4.5The creator uses a personal photo as a reference in OpenArt to generate a cinematic movie character floating in a bubble using the Seedream 4.5 model.OpenArtImage to Image
  3. 15:322:48Create video transitions with Start and End framesThe creator demonstrates how to use the 'Start Frame' and 'End Frame' feature in OpenArt with Google Veo 3.1 and Kling 2.5 to create a seamless transition between two different AI-generated scenes.OpenArtImage to Video
  4. Watch “How to Start Making AI Videos in 2026” →

Text to Image

  1. 3:130:52Generate character hero shots with Nano BananaThe creator demonstrates how to input a detailed descriptive prompt into Nano Banana within the OpenArt interface, select a 16x9 aspect ratio, and generate four variations of a character.Dan Kieft
  2. 3:551:02Text-to-image generation with Nano Banana ProThe user generates a realistic photograph of a man fishing from a pier using the Nano Banana Pro model and the autoenhance prompt feature.Affiliation
  3. 2:000:31Generate a 3x3 scene grid in Open ArtThe creator demonstrates how to use the Nano Banana Pro model on Open Art to generate a 9-panel grid from a single prompt, specifying 4K quality and a 16x9 aspect ratio.Mira AI
  4. 2:420:53Generate images with Nano Banana 2The creator demonstrates how to generate a cyberpunk Buddhist temple image by entering a text prompt and selecting the Nano Banana 2 model in OpenArt.Wade McMaster - Creator Impact
  5. 2:180:24Generate realistic images with Nano Banana 2The creator demonstrates how to generate a high-resolution 4K image using the Nano Banana 2 model on OpenArt with a specific cinematic prompt.Isa does AI
  6. 0:350:16Generate fruit images using OpenArtThe user shows how to use the Nano Banana 2 model on OpenArt, pasting the prompt and setting the aspect ratio to 9x16 to generate the character image.AI Rush Hour
  7. 1:300:48Generate AI fruit characters with OpenArtThe creator demonstrates how to paste prompts from ChatGPT into OpenArt, select the 'Nano Banana 2' model, and set the aspect ratio to 9:16 to generate high-end 3D animated fruit characters.Wifi Uni
  8. 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.Dan Kieft
  9. 5:060:57Generate AI image from PDF prompt in OpenArtCurrentThe creator demonstrates how to upload a PDF to ChatGPT to extract a prompt and then pastes it into OpenArt using the Nano Banana Pro model to generate a 4K image of a person on the moon.Dan Kieft
  10. 1:420:31Generate images with C-Dream 4.5 and 4The user demonstrates generating a complex scene with a universal prompt using C-Dream 4.5 and C-Dream 4 (BiteDance) within the OpenArt interface.Roboverse
  11. 10:010:23Historical scene generation with Imagen 4The creator tests Google's Imagen 4 (Image M4) for prompt adherence and historical accuracy in an Aztec-themed generation.Roboverse
  12. 1:030:58Generate images with Flux and anime models in OpenArtThe creator demonstrates using OpenArt's text-to-image generator to create a cyberpunk detective using the Flux model and then switches to an anime style model using the same prompt.Thomas Creates