Firefly generate vector hard to find and not working.

Thank you for getting back to me. This process lead me into a rabbit hole of testing the boundaries of prompt understanding between the generate image and text to vector apps using different models.

First, it was literally the word “dead” that created the problem. My prompt asked for a cartoon-ish image of a dead squirrel with Xs for his eyes. When I clicked Generate, I immediately got the Adobe image of a rainbow-hued puppy with big sad eyes and the message "Something went wrong. Please try again later". No other clues. I kept trimming my prompt down to the bare minimum and discovered that the word “dead” was the problem. Not the Xs for his eyes (which it didn’t really understand), but when I removed “dead” the text to vector generator tried, and failed, to create my image.

I was using Firefly Image 3 model and it hardly understood the prompt. Images were created, but it was not even close to the instructions from the prompt.

When I go back to the image generator with a Gemini model versus the text to vector generator with the Firefly model, my long prompt - including the word dead - did a much better job of generating a usable image. I am trying to create a paint stencil and struggle a bit with the prompts to get images with the proper single silhouette color, but that will just cost me time and credits to get that right.

So, this does make me wonder if there is a future for text to vector. Should I even try to use it, or is the new experience generator the future? The new experience comes with a simple toggle between “image” and “video” without any other knob to generate vector images specifically.

Again, thanks for your help.

Hey ​@majorBanzai 
Regarding finding the Text to Vector, I agree it is a bit hidden. 

Help us. Help you.

Something went wrong

A Full Screenshot or short video:  Please provide a screenshot of your entire browser or application window, including your avatar in the upper right corner. Many errors have multiple causes; seeing the full context is much more helpful than a zoomed-in image of the error message alone.
>>Make sure to remove person details: email address, name... before posting<<

• System Details: Specify your Operating System (OS) and Browser (including version numbers).
• Workflow Context:
  • Which Firefly function were you using? (e.g., Text to Image, Generative Fill, Text to Video, etc.)
  • Which model was selected? (e.g., Firefly Image 3, Image 4 Ultra, Imagen 3).
  • The full prompt you were using.
  • Copies of any reference images, keyframes, or original images used.
     

Note: Here’s a useful article explaining the most common reasons that trigger the error you’ve been seeing.

Suggestions on How to Prompt
https://community.adobe.com/questions%2D404/use%2Dadobe%2Dfirefly%2Dto%2Dgenerate%2Dyour%2Dimages%2Dand%2Dvideos%2D1476088?tid=1476088&fid=404

Common problems

• Trademarked / Copyright
• Political figures / Celebrities 

• Long complicated prompts (often from ChatGPT)
  (short easy to read prompts tend to work very well)
• busy dark background images for videos. the images need to be easy to distinguish who the main characters are and what the background is. 

Anything to do with Children

• if it has children or child like images (an absolute no/ firefly will not generate anything that even resembles a child/ even childlike)

or

• - the prompt has words associated with children example: boy, girl, kid, kids, child, children and so on...
  Many Generation Models will not generate anything to do with children.
• Nudity

Cheers

Nate