Both of those are great images. The AI enhancement does add a little more realism - not quite photographic, but perhaps a bit of additional texture to the skin and certainly it adds realistic shadows to the main figure making her fit more realistically into the scene (in contrast to the crux girls in the background who don't have shadows at all - maybe manipped in for some additional detail/context?). It shows the kind of subtle but important enhancements that AI can add.
The AI can be frustrating at times, at least with the free version I've been using to experiment. You need to go through several "generations" before you find something you like, and continuously have to either add to the prompt or put in negative prompts for features you don't want in the scene. Sometimes, AI puts in some extra limbs or finger digits, or some really weird disturbing images, lol. If you have a lot of time and patience, you can get some amazing scenes out of it, even with a free version. I'm working on a picture storyboard with which I want to do a long story, and maybe get some volunteers for some victim role playing, which could be a lot of fun.
As I mentioned in other threads, prompting is only a small part of AI image generation. Things will probably change in the future, but for now, you won't get very far if you rely on prompting alone.
In my case, I perform about 80% of image-related tasks with a local installation of Krita AI + ComfyUI on my RTX3080. For more resource-intensive tasks, I use RunPod.io.
Great art! You should have told what was going through her mind as her body slid down the stipe as she is raised!
I used in-painting to add those 2 but is has some shortcoming like the lack of shadows and the shading
I hope this doesn't come off as a criticism of your art since I only intend to share tips about dealing with technical issues related to this render.
A great, well-done image. One of the very best on this site. Utterly captivating. I've come back to it many times, enjoying its realistic depiction of a young woman hanging nailed to a cross. I imagine she's just been crucified rather than hanging for a period of time. Still fresh, in shock, still not believing this has really happened to her, nailed naked and exposed.Another AI generated image with some tweaking of the hands (nails mismatch caused by a shortage of nails not artist error
View attachment 1465103
Thanks! Fooocus as 3 option when you inpaint:I hope this doesn't come off as a criticism of your art since I only intend to share tips about dealing with technical issues related to this render.
I believe the leading cause of the problem was the context chosen for inpainting. Choosing an appropriate context when inpainting is important to preserve the overall image consistency.
For example, if you select only the background girls and try to inpaint, the result will likely not look realistic. The reason is that the area (or the "context") is too small and contains few hints to determine the correct lighting condition and relative distances between objects.
Certain UIs like Krita allow advanced tools to deal with this problem. But there's also a neat trick you can use in any UI:
View attachment 1495575
As you can see from the above image, you can select extra regions to expand the context without affecting unwanted areas around the subject. In this case, I added two extra regions to make the context area (the red rectangle) include a part of the front girl's body and the men in the background to give the AI a better idea about the relative position those two crucified girls are in.
Also, it's important to keep the context as consistent as possible in terms of lighting conditions (i.e. light direction, tone) and focus effect (i.e. depth of field):
View attachment 1495574
The original image contained a few problems regarding this aspect, likely confusing the AI when using the area as a context for inpaiting. It's best to avoid local inpainting with too small a context to prevent such issues (that's why it's best to use regional prompting as much as possible). But in case the image already contains inconsistencies like the above example, it's best to manipulate it using editing tool to "fix" the problems before running the output through a low noise inpainting.
You don't have to be skilled at photo editing to fix shadow or DOF problems. To remove a problematic shadow, for example, you can simply paint over the area in the same colour as the background. You don't have to worry if it looks cartoonish, as a low-level denoise will make it look realistic enough.
Similarly, you can draw missing shadows, making distant objects more blurry, and so on to recover some of the lost inconsistencies like this:
View attachment 1495577
(I didn't care to fix all the details or preserve the nails, since my intention isn't compete with Hornet1ba's fine original work.)
Hope this may help anyone having trouble with similar issues.
With AI you never know what you will get, i agree that this one turned out OK.
OK! I disagree, sir! Most vehemently! It turned out awesome!
Messa seems pleased her body is so nicely displayed. Barbara is a little concerned what they have planned for them...All inclusive vacation at a tropical island (another case of not reading the fine prints
View attachment 1496191
I think she can ... but for me, I'll be admired nailed to my cross and it will be wonderful !!!
The young woman crucified for frivolous crimes disagrees. She hangs naked nailed to the cross. Her petite body seems heavy as it pulls at the spikes through her wrists. Already she has to relieve herself but there are mere commoners staring at her nude body. The cross is made of crude wood. The bark scrapes at her flesh with every move she makes. And the insects have yet to find her bare skin...
Now we just need a way to do hands and feet properly!
That PonyXL new sdxl checkpoint seems to be better at hands, i don't know about feet yet.
