Feature Requests

It would be great to be able to download a complete font set from my generated fonts 🙂

I suggest giving the user the OPTION TO CHOOSE between (A) fx generation for the WHOLE WORD, understanding the whole word as ONE OBJECT and then apply the visual effect  OR  (B) fx generation for SINGLE LETTERS, as available today Benefit: in some projects, e.g. a jungle scene, many elements such as leafs, snakes, tropical birds, etc. are repeated again and again on each individual letter which sometimes is just too much. Instead, I'd prefer to have e.g. lots of green leaves across the complete word, with only a FEW tropical animals on just some of the letters. In this case the COMPLETE WORD would be recognized as ONE OBJECT I could imagine prompts like "dark tropical jungle with huge leafs in different green tones and 3 red parrots, 2 green snakes and 1 alligator", for example - everything related to the word as a whole I think this offers more variations and better harmonization with the overall layout Thanks for considering!

It would be cool if it would break down the image into layers for animation after the image was created. Maybe like a PSD or AI file. Like if you asked it to create a character and it came ready to rig in Adobe animate. Speaking of character. It would be really cool if the cartoon style had its own style. I know different cartoons are commercial but if you had artists create different styles that would be really cool. Maybe there is a way to take cartoon styles and give them different names so they are generic. It is an art we can do anything. 

Thank you for sharing your idea for an AI image generator in Adobe Firefly. Here's my perspective on your proposed features:1.Changing the lighting in images is a commonly requested feature in image editing software so that it would be a useful addition to an AI image generator. This could include options for adjusting an image's brightness, contrast, and color balance to improve its overall look and feel.2. Auto font discovery and creation is an exciting idea, but it may not be easy to implement. While AI has made great strides in generating realistic images and text, font design is a highly specialized skill involving technical and creative expertise. It may be more feasible to offer a library of high-quality fonts that users can select from or to allow users to modify existing fonts with AI-powered tools.Overall, an AI image generator with features for changing lighting and improving font selection could be a valuable addition to Adobe Firefly.Madsam

I have an SVG file that contains an error: several paths that should have an identical stroke coloe, only have similar colors. When using "Recolor artwork" in Illustrator, the colors are grouped correctly.  Firefly does not group them correctly. It would be great if it could get the color ordering mechanisms that exist in Illustrator's Recolor artwork feature. In the screenshots you see the red roads are grouped correctly in Recolor artwork. In the second screenshot you see that recoloring is off for one of the roads.

Try taking a word as a whole image instead of image per letter. Say a contiguous wood grain across the four letters for wood or trees. 

hi, is it possible to enlarge the preset icons from the styles and themes?

It works fine but I want to mention that "Recolor" in Adobe Illustrator can do more AI work than Firefly in this field. I suggest you to import all Recolor features. That can do it more creative espessialy for thous who are not familar with Illustrator Recolor.

importing different vector formats " .ai - .pdf - .eps"It is easier for the user - instead of converting an Ai or EPS or PDF format into an SVG formula, using Adobe Illustrator every time, which takes time Most of our files format are .ai

It would be great to add a toggle/button to show/hide the user panel on the right side. Giving a bigger space to see the images and show it when needed.

Using Pattern generation in AI or compositing in Photoshop, Illustrator, or AfterEffects to create tiling textures for the library so you can apply original styles to text. Shaping tools for 3D effects like Bevel, Balloon, Textures, etc.

Adding more control over image and using segmentation like in Stable diffusion. The images produced in stable diffusion are rather more clear and abiding to the prompts than here. Enabling developers or companies to develop extensions would help this way better. Everything I stated are made by independent developers who open sourced their work with limited resources.

Would be great to generate flat effects and select an area like specific words or even letters where these effects are applied. Like the tentacles on the attached logo that are used on a specific word or even outside of the logo. 

1：支持线稿生成方案2：支持局部风格微调3：支持区域重画4：支持图片快速融合，融合区域可控

As title, would be cool to see how many of your creations are accepted/ Thanks for this amazing software/tool.

Hi.  I'd like to suggest a Reset or Clear button for the prompts. There's one only for the styles. Users like me, who like elaborate prompts sometimes, will find it really useful.  Thank you.

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.

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.

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.

I'm having success generating textures, but I have no real control over the scale. Most results are too close, and trying various prompt elements to zoom out, reduce scale, etc. have no predictable outcome and are usually ignored.Please consider a development fork that allows users to scale textures (and possibly apply orientation, angle of view, etc).

The Clear styles button has the same shape as image effect buttons, which can be misleading. It took me a minute to understand that Clear styles is not a clear style that is applied to the image, but an eraser tool. It could also be helpful to make effect categories like content type, style, composition, etc. more distinguishable below the prompt field, so we have a better overview of what type of effect is already applied.

I'm not sure if this has been requested before, tell me and I'll remove this.A text underneath the prompt input bar that says something like "Based on your prompt we suggest these styles:".I did a very fast mockup on that:  

(Similar to how the Style filters are added as boxes below the typed text currently), It might be handy to test if he typed text works as similar style blocks -- however, it would be nice to keep options there with checkbox field rather than removal close-cross. (When desired combinations are identified, one can "UNDO" and "REDO" by toggling the checkboxes.

[stockid=424051447,102414488]

Firely is amazing in creating textures/pattern!It would be amazing if he can understand the prompt «seamless repeatable pattern» and create a seamless pattern that could be use as a pattern in Photoshop.