Questions

Not so muich a bug but generic feedback on training the AI.   I entered the following term to generate a picture. a male reading a newspaper leaning with his back against a tall narrow lamp post   The images had all the main items, man lamp post, reading a newspaper but only one image had his back against the lamp post, the others ere in all sorts of poses. A tall narrow item also does not seem to be the best way to describe something as narrow varied from wider tha the human to something only slightly taller.    Is there better ways to describe what we take a generic cocnepts? 

Just wondering why when I input the word 'scribbles' firefly tells me if only understands English?

je trouve que dalle e 2 et firefly ont le meme style de qualité d'image, que pensez vous ?

Would it be possible to have a definer field that specifies CONTEXT?in the example below, the first result was within the HARDWARE toolshop space... making use of he following: "TOOLSHOP with volumetric lighting and shiny floors, stacked with heaps of NUTS & BOLTS"--by replacing the last part with "WASHERS", the result veered away from the hardware context, and supplied another meaning --  taking context to the laundromat meaning of the word:

Hello friends I've tested few of my most successful prompts (on Stable Diffusion) with FireFly but they all blocked. I'm interesed in character design and female cyborg characters especially; results related to this concept are very bad, downright ugly and unusable. Prompts based on photography concepts like "flower, sunset, glowing, golden hour, soft focus background" works very well. My cityscape attempts was fine but cyperpunk and synthwave style cityscapes seems to hard to come up with - especially on realism and detail-wise. Overall works very stable and very fast.  Thank you for the opportunity.

I noticed that there is a link to discord on your beta page? Does that mean you are in a collaboration? And would it then be possible to get the same photorealistic appearance of the images as in Midjourney 5?

I already have a discord account for Midjourney and for a Patreon membership discussion area. When I put in my email for firefly (the same email that I use both on my Adobe account and on Discord, I get the error message that this email already exists--but it won't let me continue. What am I supposed to do here? Thanks. --Sherry

Hi, I love Adobe firefly ! It's easy to use. Seems like there is unlimited refreshs because I did try to 100 and got tired had to stop. The renderings exceed my expectations. Beautiful photos, Art , techniques. Lots of great choices. Prompts are easy you just type like a regular sentence. I hope there's a save my creations in my own gallery on the site in the future. One constructive criticism hands are distorted , 6 fingers , sometimes human anatomy needs to be better. Other than that it just fabulous! I am having so much fun. Superior program.

Do you have plans to release it in Brazil? I have a youtube channel dedicated to A.I, I would love to do a review showing all the good that exists in this wonderful tool!

Hope it can release to comercial use

I am amazed at the number of times you can refresh an image on the new adobe firefly. I pushed the refresh button over 100 times ,got tired, and they were all different. More detail, less detail . A simple "mountains with white flowers " graphic widescreen (16;9) . Great job! I am Amazed! Thank you Adobe!

Re-posting from the Firefly Discord channel..   There is a livestream a bit later today with intro to Firefly and how to work with it https://www.behance.net/live/videos/19937/Introducing-Adobe-Firefly