Copy link to clipboard
Copied
Hi you guys.
So, I have been trying out the new generative fill tool and I think it is really cool. Unfortunetly I feel like almost everything I add (except for probably 1 in every 200 items) comes out with a horrible result. I have watched a couple of videos on f.ex YouTube where I feel like the way they are able to select and replace items are doesn't really work for me. As an example: If I select over a piece of clothing and put in information to change the piece or for example a colour, the result that comes back out is consequently abselutely dreadful, twisted, and never heeds the command that it is given (as an example, when asked to change the color on a piece of clothing from black to red just using "red sweater" as an example, the three examples twists the image and still comes out as black).
It is kind of frustrating, because it seems like I am doing pretty much the same as in most of the videos, but it is almost as if it doesn't understand the language I write in (English for my part). Another strange thing is that if I ask the AI to change the color of say a t-shirt, simply marking the t-shirt area, what it will do is usually keep the colour or perhaps change the color, but completly disfigure the tshirt.
Does anyone have the same kind of experience and might have any thoughts about how I can change or improve this? Would love any sort of feedback.
Copy link to clipboard
Copied
Hi @RA32027363hd6z AI is going to generate new image results when using - not simply recoloring items. There are other more capable tools already in Photoshop to accomplish this.
Copy link to clipboard
Copied
Thanks for the quick answer. I understand, but from videos I have seen that simply by marking an area around, say a sweater and giving the instructions "purple sweater", the AI seems to be able to create another sweater (different variations) that actually fits into the picture. I have also seen the same when changing haircuts/adding hair on a bald person, but when I do exactly the same, even with the same picture, then it seems like the options I get to choose from are almost as good as useless. Generally speaking it seems that the tool should be more than capable of producing viable options and that it does (in the videos), but whenever I try to use it in the same way the results I get are way off point. It might just be a case of hit and miss, but it is not like the results are "close but no cigar", they are simply way off almost every time.
Wierd thing huh? 🙂
Copy link to clipboard
Copied
Can you supply some screen shots of before and after with prompts given?
Copy link to clipboard
Copied
I have the same problem. Like everyone else I am new to Gen Fill, but I don't know why the results I get are so terrible, completely different from what I ask for.
Copy link to clipboard
Copied
Robert, there is definitely a trick or two to get the best out of it, and more than it would be easy to tell you about in these comments. There are two YouTube channels — The Photoshop Training Channel, and Photoshop Cafe — that are hands down the best source of Photoshop tips and tricks. Flick through their recent uploads looking for Generative Fill, Remove Tool etc. and you'll soon find yourself getting much better results.
Having said that, we need to remember that it is not the right tool for every situation, plus we have the issue of burning through limited Generative Credits when using Generative Fill. I have found that Edit > Content Aware Fill has given me much better results in some situations, for instance. Several Photoshop tools a functions use Ai, and work like magic IMO. Select Object was good, but Remove Background is sensational, and those tools do not use up Gen Credits.
Copy link to clipboard
Copied
@robertr93748881 Adobe has supplied this guide to help writing effective prompts in Firefly and Gen Fill. This may be helpful:
https://helpx.adobe.com/firefly/using/tips-and-tricks.html
Copy link to clipboard
Copied
I'm experiencing the same issue. I've sent so much feedback to Adobe on the generated content but then the options begin to progressively get worse. I see some people in the comment section here saying "oh you just dont know how to use it" but i bet they havent used it since Beta because thats when it used to work decently. I feel like Adobe has purposefully rigged it to encourage users to create their own content and to avoid generating content too close to existing content. Either way, the programming needs to be updated or it's going to keep getting worse
Copy link to clipboard
Copied
@Alexand10m can you share some examples including the prompts used to generate?
Copy link to clipboard
Copied
Copy link to clipboard
Copied
@Emils38377693g3pq to be fair I don't even know what you would consider a "studio background".
You need to be more explicit. Do you mean seamless? solid color? faded gradual color?
Copy link to clipboard
Copied
I have the same issue.
Find more inspiration, events, and resources on the new Adobe Community
Explore Now