Participating Frequently

Answered

keep getting this message when trying to generate an image "Can't load We can't display the generated image. You can edit and try again."

Forum|Forum|13 days ago
July 17, 2026
8 replies
43 views

keep getting this error while trying to generate image with flux2 pro or nano banana pro or get image … “

Can't load

We can't display the generated image.
You can edit and try again.”

Correct answer Hajar Toutsi

Hi armango,
Thanks for reaching out about this.

When you see the error “We cannot display the generated image. You can edit it and try again.” it means that your prompt or reference image contains something that doesn’t align with the AI user guidelines (copyrighted, sexual or violent content etc..), In those cases, the filter stops the generation until the prompt or image is adjusted to meet the guidelines.

If you’re unsure what might be causing the issue, you’re welcome to share your prompt or reference image(s), and I’ll be happy to help you adjust it so you can get the results you want.

We're happy to help.

Hajar
[Moved to questions]

Hajar Toutsi

Correct answer

Community Manager

Hi armango,
Thanks for reaching out about this.

When you see the error “We cannot display the generated image. You can edit it and try again.” it means that your prompt or reference image contains something that doesn’t align with the AI user guidelines (copyrighted, sexual or violent content etc..), In those cases, the filter stops the generation until the prompt or image is adjusted to meet the guidelines.

If you’re unsure what might be causing the issue, you’re welcome to share your prompt or reference image(s), and I’ll be happy to help you adjust it so you can get the results you want.

We're happy to help.

Hajar
[Moved to questions]

A

armangoAuthor

Participating Frequently

Hey Hajar

thank you for coming back with support ! please see below more details as per your request:

1. there is nothing that violates the guidelines . It works with same prompt like and another time it doesn't and it may last for 10-20 minutes till it start working again .
2. attaching a full screen shot
3. system information and browser information please see attached
4. Text to image with reference , please see attached the screenshot for details
5. The bug happens when using flux 2 pro and GPT image 2 and Nano banana 2
6. prompt examples : “locate the pattern from the image 1 to kimono on the image 2, the centre of the seed from image 1 should be located under the right sleeve of the kimono with black and white patterns going from the centre of the seed to be spread across all kimono. keep exact colors from the image 1 , keep the pattern complexity from image 1. keep exact shape of the kimono from the image 2 .”

hope this helps !

Hajar Toutsi

Community Manager

Thank you so much for sending over the detailed screenshots, system info, and example prompts, armango. This gave our engineering team exactly what they needed to investigate your account logs, and I have some clear answers for you.

First, regarding the intermittent 10–20 minute outages: this is not an issue on your end. Our logs show temporary connection delays and traffic spikes between our platform and the AI model providers (like Flux, OpenAI, and Gemini). When this happens, generations can fail or hang until the connection resets. Our engineers also identified a small background bug on our platform related to clearing out those timed-out sessions, and they are actively working on a fix.

Regarding the guideline violation messages: While the specific kimono prompt and reference details you shared appear completely benign, our logs show that an automated safety filter on the Flux model flagged several generation requests on your account for sensitive content. Automated, third-party AI safety filters can sometimes be overly sensitive and trigger false positives, occasionally misinterpreting innocent reference images, complex fabric patterns, or garment contours as policy violations.

What you can do moving forward:

Try an alternative model: Because each AI model uses a different safety filter, if you believe a benign prompt or reference image is triggering a false positive on Flux, try switching to one of the other models in the workspace. They often process reference images differently.
Refresh and wait for timeouts: If generations suddenly stop responding across all models, it is almost certainly one of those temporary server-side delays. Waiting a few minutes or refreshing your browser is currently the best workaround while our team rolls out the stability fix.

Thank you again for taking the time to report this! Please let me know if you have any other questions.

Hajar

O

Oh.N8

Hey @armango
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

A

armangoAuthor

Participating Frequently

Hey Oh

thank you for coming back with support ! please see below more details as per your request:

1. there is nothing that violates the guidelines . It works with same prompt like and another time it doesn't and it may last for 10-20 minutes till it start working again .
2. attaching a full screen shot
3. system information and browser information please see attached
4. Text to image with reference , please see attached the screenshot for details
5. The bug happens when using flux 2 pro and GPT image 2 and Nano banana 2
6. prompt examples : “locate the pattern from the image 1 to kimono on the image 2, the centre of the seed from image 1 should be located under the right sleeve of the kimono with black and white patterns going from the centre of the seed to be spread across all kimono. keep exact colors from the image 1 , keep the pattern complexity from image 1. keep exact shape of the kimono from the image 2 .”

hope this helps !

A

armangoAuthor

Participating Frequently

same issue here on latest safari browser .. super annoying , probably doesn't worth to continue subscription . any solutions yet ?

Sign up

To post, reply, or follow discussions, please sign in with your Adobe ID.

Sign in to Adobe Community

To post, reply, or follow discussions, please sign in with your Adobe ID.