Skip to main content
Giddy_personality5D25
Adobe Employee
Adobe Employee
March 23, 2023

P: Photo realistic humans not optimal

  • March 23, 2023
  • 77 답변들
  • 15047 조회

Whenever i try human photos, there is some wierd manioulation of fingures, faces, perspective etc which make the picture looks little odd. I hope the team is still working on fine-tuning it. I know it is to avoid copyright/content authenticity issue but the images are not looking great due to that.

77 답변

Participant
August 19, 2023

Human faces are not real, please work on that.

Participant
August 16, 2023

when i gererate fill with backgroup my head is mix and distroted with background

Participant
August 16, 2023

Habe jetzt, zwei drei Bilderstellung auf Basis von Text erstellen lassen und die Gesichter werden nicht immer optimal dargestellt. Sehr oft sind diese matschig.

Participant
July 27, 2023

hands are often distorted and incorrect 

B Siva31180936lt9t
Participant
July 19, 2023

like this

Participant
July 11, 2023

Firefly is not able to generate a proper human face through a deatiled prompt. The Facial features are being distored and not acuture to the reality. 

 

Merging all similar threads here so we can keep the community updated on this bug.

Participant
July 7, 2023

Agree with the consensus that the face generation for either photo or illustration are very distorted and no usable. Am keen to  use this for generating images from text to image but right now that is not possible. Everything looks so odd and distorted, even when a keyword is 'lifelike' or 'realistic', no joy yet.

Participant
July 1, 2023

Hey team Adobe,

The fingers shown in images are scary please improve this error

 

JR Boulay
Community Expert
Community Expert
June 29, 2023

Why can't I add feet and legs to this little girl?

I've read the guidelines but I can't find anything about feet or legs.

 

Acrobate du PDF, InDesigner et Photoshopographe
Participant
June 28, 2023

First of all... well done to Adobe! A great start.

 

Background:

I'm in the Educational Publishing space in South Africa and finding local, traditional stock is notoriously difficult. So I thought to generate a test image with the cultural attributes which come up in every artbrief.

I like the setting and the overall look-and-feel of the image that was generated.

 

Generation term: "South African Xhosa woman cooking on an open fire in the outdoors"

 

Some critique...

At first glance the images are fine until you look at the proportions of the arms vs the body of the subject. This will have to be refined in future iterations of the software, but as is, is a fantastic visualisation tool.

 

I attach the four options the AI presented for anyone interested.

 

Merging all similar threads here so the team can access all requests on this issue.