Feature Requests

Give me a Rough idea about Using The Ai system

At the first step of entering the prompt, there is no option to select the content type…. Even if I enter a prompt mentioning photo in the beginning (example: photo of a bird in a tree) it automatically switches to art style at generation page (as seen in GIF below)…         “please provide an option to select the image content type at the beginning stage like (none, photo, graphics, or vector)”  

Hello, first of all, thanks for giving me access to the beta, I really appreciate it. I've been enjoying how great this tenecoligia is for 3 days. 1 It would be great if when you create something with this technology that you have several formats such as photoshop in intelligent layers to be able to edit things 2 It would be great if I could upload my photos and be able to retouch or edit them with this technology, it would be great. GRACIAS ❤️

Things like google display assets that have various artboard sizes. An automated generator to insert a set of assets or text from a moodboard and putting in the different sizes. Canva does it in a very poor way.

the use of firefly with Adobd XD to make animations, and ideas done faster and increase the workflow of UX designs. if the Ai can help with suggestions and do commands.

It would be great if we have option to clear all selected setting at one click and also it will great if we have option tosave our selction setting in the text to image AI

Based on an image, I would like to generate a website theme based on an image.For example, I have a videogame with a main character and I would like to generate a website layout / design based on the image of that character, extracting colors, art style, elements, etc. applying it to a cool modern website. 

Hi Adobe Firefly team, I would like to share some feedback with you regarding the text to image generation feature in the photo generator. I have used many high-quality prompts for image creation, but I have noticed some issues with the characters generated by the system. Specifically, the textures of the face, eyes, hands, and other details are not well-defined. Additionally, I have noticed that some images are repeated.I would appreciate it if you could address these issues in future versions of the software. On a positive note, the colors are very natural and realistic, and the lighting is better than the mid-journey natural lighting.Thank you for your hard work on this feature. I believe that resolving these issues will make Adobe Firefly even more effective and successful after the beta version.I LOVE YOU......

I feel like the "show similar" results deviate too far from the original result. It would be nice if the variations were more slight. Or perhaps if there was a slider that would allow you to adjust how much you would like the results to stick to or deviate from the original design output.

Using the text effects tool in Adobe Firefly: The ability to resize text would be helpful, also the option to allow longer text to drop down onto another line. When trying it out the type sometimes got cut off.

Currently, some options cause an automatic Refresh/Regenerate, such as moving the Strength slider for the reference image or choosing a different style. This causes unexpected additional requests that take up time and compute resources. Please default to only refreshing when the actual button is pressed to avoid delays and wasting resources.

I think this should be optional to include. Why is this any different than someone taking a photo and manipulating it and selling to a costumer or consumer? This seems like you want everyone to be forced to tell clients the work was done using AI. This directly harms the designer. It devalues the work being done. This is a bad feature that will make me not use the platform. I'd rather use another image generator and edit as needed like all designers do so I can keep my prices the way they are. I don't disclose details of my projects when I hire out for illustration because it's a work for hire. I consider this to be the same, If I will be paying for the "service" I should be able to brand it as my creative work. Especially since I would be writing the prompt. To give credit to the AI more than the artist is a fail just because you'd like transparency. There has never been 100% transparency to our customers. This is a major blow to your attempt in competing in the AI space. 

On some of the 'text to image' generated images there were 5 legs on an animal and as an example it would be good to be able to share what is wrong, say with a highlight tool or circle tool

Delighted to finally test the beta. First suggestion: Change the rating system from the simple thumbs-up/-down to a one-to-four-star system or something similar; I'd like a bit more nuance than a strict up or down vote. For example, in my first prompt, I asked for a close-up of a human hand, with all fingers extended. As expected, all results were weirdly formed, and one had seven fingers. They were all "wrong" (albeit amusing, as I expect this to happen with all image generators), but the one with seven fingers is more "wrong" than the others. I'd like to be able to express that in a quick rating.  Of course, this certainly is not a deal breaker; otherwise, the whole system is very impressive. More commentary to come.

thank you for inviting me to be a beta tester for adobe fireflyI explored the Generated Image with AI website a lot. I even use stable diffusion to make really good pictures. either realistic photos or vectors.some of the shortcomings that I see from text to image1. It seems that Adobe Firefly has very little material, for example: if I use the command "Create a realistic image of a young asian woman sitting on a park bench in autumn. Use a Hasselblad camera with a 85mm lens at F 1.2 aperture setting to blur the background and isolate the subject"the face of an asian young woman, must be the same even though it generates a lot of times.there may be a need for a lot of resources and of course a lot of users so that more and more materials.2. There are some things that I found that Adobe Firefly can't make.- chibi (in generated many times it looks the same)- logos3. Adobe Firefly doesn't have a detailed description of prompts, such as midjourney https://docs.midjourney.com/docs/prompts4.

Here's an off-the-wall suggestion: train the AI to recognize the titles of literary works, and generate scenes inspired by the text of those works. Thus "The Raven" would show the bird on the bust, etc. Would be fun, and might be helpful for teachers and students.

Hi,It would be better if you could introduce a feature to create a logbook interior by using text prompts. This would be better suited for Adobe Indesign. The log book interior usually includes Tables with column namesBoxesTexts with different styling Space to write prompts, etc Hope you could make this feature very easily. Expecting your favourable response. Thank you

I think it would be convenient to be able to save a combination of frequently used settings as an original style.  

Hi,I feel it would be to beneficial Adobe's excellent reputation to give some free hours to those of us who have rated firefly in beta. Midjourney gives away a free hour a day if you rate the images if you even have their lowest monthly subscription. Respectfully submitted 

I feel like the majority of effects applied to text isn't super impressive. Maybe if you could control how much the object applied to the word it could help give a bit more control over how the clipping of the object appears on the text. It needs a bit more variety and area to flow off the letter.

Photo illustrators and compositors often need background elements that are either flat backdrops or open scenes that leave space for inserting other objects. Having a Style preset that helps Firefly understand the intent of its output would be very helpful. The result should have additional options for moving the "open" area around the scene easily.

It would be awesome to be able to make mockups from good quality fotos

when changing the type from  I.E. art to photo, make it so it does not change the results displayed at the moment.

This would be perfect for creating digital badges!

I don't know if someone has already mentioned this but in my exploration of Firefly Text Effects, it might be useful to have a slide for the number of items that appear. I was experimenting with the word 'lock' and then adding 'padlocks' as the effect to apply. The effect was successful and looked pretty good, but the number of locks was a little too high. It would have been useful to reduce the number of locks that appear and therefore make more use of the shapes of individual locks to create parts of the letters (particularly the classic curve of the top part of a lock to shape parts of the 'o'). I appreciate this is probably quite tricky to implement but if its possible, would give a little more control and potential impact to some of the results.