Exit
  • Global community
    • Language:
      • Deutsch
      • English
      • Español
      • Français
      • Português
  • 日本語コミュニティ
  • 한국 커뮤니티
0

How to modify an AI generated object?

Explorer ,
Apr 08, 2024 Apr 08, 2024

When I've generated an object with Adobe Express' or Firefly's "Text to Picture" AI, and when I'm very satisfied with the result - how can I modify that object preserving the same style or "look"? Or, how can I generate another picture of same or similar style, containing the previously generated object? To give an example: When I've made Adobe Express or Firefly generating a fantastic animal, I would like to generate very similar pictures, with more animals of the same type for example or with that animal in another pose or with another background.

 

I would appreciate any hint.

TOPICS
Generative AI
2.0K
Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines

correct answers 1 Correct answer

Explorer , Apr 16, 2024 Apr 16, 2024

Within the Firefly community, droopydog500 informed that the feature "to identify an object like a character and have that object appear in multiple generations in different ways (like poses, etc.)" does not exist yet. So I marked his answer as correct, and now I'm waiting for Firefly's or Adobe Express' feature of creating videos...

Translate
Community Expert ,
Apr 11, 2024 Apr 11, 2024

Unfortunately express doesn't have this capability yet. If you have access to Adobe Illustrator you could try using the reference image feature in their Text to Vector GenAI tool, but you will likely lose the photographic realism of firefly in the copies. 

Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 13, 2024 Apr 13, 2024

Thanks a lot, JessCampbell,

I still tried using the reference image feature within Firefly, but the newly generated images were not similar enough. (See the related thread in the Firefly community.)

Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
Apr 11, 2024 Apr 11, 2024

Hello, you need to know Adobe Express is using the V1 of Firefly and for now you can do this kind of workflow using Firefly by add your image to favorite and after you can chosse the image and do generate similar generation. See the few screenshot, it's in french but you should find your way but let me know if you're lost we will help you 😉

Capture d’écran 2024-04-11 à 11.40.49.png

Capture d’écran 2024-04-11 à 11.45.03.png

  

Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 13, 2024 Apr 13, 2024

Thanks a lot, Alexandre Becquet,

I tried to use Firefly (version 2) as well, using the reference image feature. But the result was not similar enough. (See the related thread in the Firefly community.)

Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Apr 16, 2024 Apr 16, 2024
LATEST

Within the Firefly community, droopydog500 informed that the feature "to identify an object like a character and have that object appear in multiple generations in different ways (like poses, etc.)" does not exist yet. So I marked his answer as correct, and now I'm waiting for Firefly's or Adobe Express' feature of creating videos...

Translate
Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines