Bug Reports

My cue word：cute big dungeon creature shifted on one side of the image, dungeon background, detailed illustration, hd, 4k, 8k,overdetailed art, by hokisai and studio ghibli, cinematic, blinding lights, cartoon style.But the resulting images are mean, not cute 

on Firefly beta, text effects always give me the following error:  Can't load An error occurred while loading your result. Please wait a few seconds and try again. waiting and trying again do not help.

Hello! I just got an email inviting me to the beta, but when I try and download I'm still getting a message saying I need to request access. Any help would be appreciated!

I've been able to download the images I've specified this afternoon, and then it just stopped working. Instead of getting a jpg, I'm getting the file with the .download extension. Renmaing it seems to work. This is on the current version of Safari on a Mac running the most recent version of Ventura.

I allowed popups on the site. Not sure why I cant request access. 

Hi there, I have just been accepted for Firefly Beta (woohoo), and as I was generating some textures I could not dowload the images for myself. I do have McAffe, I have disabled my firewall but the dowload button still does not work. Do you have any suggestions what can cause the issue? Many thanks,Hajni

I'm having some problems right now. When submitting the application, you log in with your Apple account, and your email address is your private email address. It is different from the receiving email address. Currently, neither account can use Firefly

It says "expired or invalid invitation". Besides, I hate having to respond to a big, stinky poo. I'm past the age of such childishness.  

a fairy house in a dark dark mystical forest clearing, many fairies fly and sit around, mystical fog and little light, two moons in the sky light up the forest very slightly, an elf with long hair walks up the path to the right, fog creeps over the forest floor Mein Englisch ist nicht so gut aber was verstößt hier gegen die Richtlinen?

When trying to run a Firefly prompt, i'm getting the following error -- x.at is not a function. (In 'x.at(0)', 'x.at' is undefined) Is this a known issue? thanks

I have tried to use "pixel art", and Firefly often returns a "Can't load... safety issue" (see attached screenshot). When I take out the word "pixel", even using the same prompt, it generates properly.   Examples: plumber wearing blue overalls, a red shirt, and a red hat, in pixel art An Italian male plumber wearing blue overalls, a red shirt, and a red hat, pixel art side-view of a blue hedgehog, comic style, pixel art

In the image generator in Firefly, images stopped downloading. They would simply fail to download. They worked for a while and then just stopped. I logged in using Firefox and they downloaded fine from there. 

I have tried to make an image of a Viking boat look like it is in the year 1225 AD. It has not rendered to look anything like a distant year. I can do this easily in Midjourney and hope it can sometime be done in Firefly.Here is the prompt:a slender detailed realistic Viking boat sailing into Black Sand Beach of Reynisfjara, Iceland, year 1220 AD, far distant view of ship and crew, stormy weather, dark gray blue gloomy light, low clouds

"Firefly is for non-commericial use only while in beta."should be "non commercial!"

I was sent an email stating that I have access last week (my email is brianrinaldi@gmail.com) but I have been unable to access it. It still tells me to request access.

I'd love to see the FireFly file names truncated to 100 characters on saving files given the potential complexities of prompts these days with GPT-4. As it stands currenlty PC=260 | Mac=255 and if you have anything longer you gent into a lock up sitution. 

Bonjour je me suis inscrit pour participer à la beta avec l'adresse julien@cojito.fr mais je me suis connecté sur le discord avec contact@cojito.fr je crois pouvez-vous m'aider à réinstaller merci

Hey there, I got an error with my connexion adress.I can't connect with firefly because of a dot "." On my mail adress.Firefly beta granted adress: remy.poncelet@gmail.comAdobe account :remyponcelet@gmail.com Could you do something for me please ? Thx a lot 

First time i use it, when i click on download, it simple and easy download the image. Now, everytime, it load the downloaded image on the same page of browser, losing the other 3 versiosn that it had shown in screen.

Hey, I was trying this prompt:"baby cat, white background, splash style paint, paint explosion, fantasy concept art, 8k resolution, heavy strokes, drip paint, splash arts" Now my trouble is that the prompt generates a very low variety of cast's (same colourscame) and the art style is really simular. I also found that the drippaint style isn't adheared even when I remove the other modifyer. GreetingsDries goossens

I put in the prompt "Soviet Style propaganda poster of a female cosmonaut, illustrated, illustration" and got this: Here's the same prompt on a Stable Diffusion checkpoint: And here are some Firefly generations of "a dwarf carrying a rusty axe, fantasy art, d&d style, tolkien, warhammer" Like..come on.  It's obvious different races are being autoinjected into prompts just like Dall-E.  That might even make sense to do so from a technical perspective (and note just a "woke" one) if it's necessary to make people always just a mixed amalgamation.  But it clearly goes too far.

When requesting access from Chrome or Safari I end up with an error page. Chrome says:  "This site can't be reached. Check if there is a typo in survey.adobe.com." Followed by DNS_PROBE_FINISHED_NXDOMAINSafari says: "Safari Can't Find the Server. Safari can't open the page HTTP://survey.adobe.com/jfe/form/SV_2tNbybqEq6ovet0 because Safari can't find the survey.adobe.com."

"closeup of dragon scales with gold wire"Has produced "We encountered a safety issue with this image. Please try again." error without other explanation. Repeating this prompt generates 1-2 image blocks with this warning.

I hestitate to call this a "bug" because it's more of a very minor UI thing, but I guess close enough. Either way, this definitely isn't anything critical, but figure I'd point it out. For Context: In most cases a style will be applied to the generation, which means that below the prompt text box, it shows a list of the styles and a "clear styles" button. I'll attach an image to show what I mean.But when you have no style / content type / color etc, that bottom row of style tags (below the prompt text) is not showing, which causes the four image results to resize ever-so slightly (because they have more room on the page and expand). Problem Scenario: If you want to switch between the different 'Content Type' options to compare which version of a result you like, when going from no-style to any-style, the images do a little animation and resize. Which makes it a bit harder to directly compare a style to the none-style. In other cases, where all the images stay exactly the same

I took a Firefly image into Lightroom Classic and added a preset.  Upon export, I made sure Use all Metadata was checked on.  When I uploaded the image to Content Authenticity Verify, the credentials were missing.  When I opened the same image in Photoshop from Lightroom Classic and exported it, the credentials were intact. Just info for the Adobe team.