- Jan 29, 2018
- 79
- 80
It's my turn to publish, mixing by me,Happy Father's Day!
the most beautiful exquisite reboots...
(dedication to you Rizzrack and OhWee..)
https://f95zone.to/threads/dating-my-daughter-fan-art.4315/post-3697681
the most beautiful exquisite reboots...
(dedication to you Rizzrack and OhWee..)
https://f95zone.to/threads/dating-my-daughter-fan-art.4315/post-3697681
- Dec 30, 2017
- 6,961
- 33,607
Hey all, was playing with Stable Diffusion and testing to try and convert 3D renders to photoreal. Thought I'd share. This is right out of SD with no post processing. What you think?
- Dec 30, 2017
- 6,961
- 33,607
- Mar 16, 2018
- 4,523
- 32,363
- Sep 3, 2016
- 1,210
- 2,543
Yes, I suppose he used img2img but I wonder if he used a celeb name in the prompt or if he just let the AI do an interpretation of Dee's face.
- Nov 18, 2017
- 1,940
- 4,078
- Sep 25, 2018
- 182
- 249
No celeb or lora was used in the making of the image. I have a few negative TI that I use to keep the odder morphing down to a minimum. But other then that it is just the prompt. Oddly I have found you can get pretty close with my settings with the only prompt being 'realistic' Of course having more prompt makes it better.
If you are interested here is the settings for SD using Auto111
analogMadness_v40
prompt:
a cute 17 year old girl with blue eyes big breasts and blonde hair in a ponytail with hair-tie down her back in a red shirt with a teddy-bear logo standing in an apartment kitchen
negative prompt
BadDream FastNegativeV2 UnrealisticDream
Sampling: DPM++ 3M SDE Expontial 100 steps
WxH 768
Batch 10 (I like to run a few to find the best it's not needed to be 10)
CFG scale 15
Denoising strength 0.25
ADetailer : On
Oddly with these setting there is not much variation on Dee's face with different seeds. Mostly just fuzzy or odd eyes. I bet a lora to fix the eyes would remove that, but I was just trying to see what I could get with the minimum settings
- Sep 3, 2016
- 1,210
- 2,543
No need for a Lora for the eyes, you could just use "deformed pupils, deformed iris" in neg prompt, or use "eyes only" with Adetailer. Neg prompt is usually enough.
Also AnalogMadness is now v7 maybe it will be even better, and try Restart with 66 steps instead of DPM++ 3M SDE Expontial 100 steps, it might be just as good and slightly faster.
Also you just say 768px so I guess you did an inpainting of the the face ? Not the full image remade with realistic style ?
- Sep 3, 2016
- 1,210
- 2,543
Right, I didn't pay attention to the low denoise, that's why it still looks like 3D and not more photorealistic. did you try with like 0.75 denoise or more ?
- Dec 30, 2017
- 6,961
- 33,607
I tried enlarging Dee's eyes for a more elf look.
- Dec 30, 2017
- 6,961
- 33,607
You don't have permission to view the spoiler content.
Log in or register now.
yeah I tried higher denoise, but the higher you go the more differences you get and the more detailed the prompt has to be to keep from having more changes introduced. I did upgrade to V7 and used restart, though bumped up to 75 steps as 66 was a not as crisp. The result was nicer but still somewhere between photo and 3d. I'm running through a bulk run of day 1 images to see how it works. Looks ok but it it seems to really want to give her a nose ring.
I agree it still has a bit of the original 3d look, but I really want to get to a point where I can bulk run with as little input as possible so higher denoise is not a great option. I am curious what would happen if I were to run an image through multiple times at a lower setting and see if it got more photoreal each pass.
- Sep 3, 2016
- 1,210
- 2,543
I think there's a way to do that automatically with Controlnet but I've never tried. I also think the quest to be able to batch process all the images of a game or even just 20 and expecting a consistent result is a bit futile right now. But kudos to you if you manage it.
In any case , controlnet like Openpose, Depth and Canny help to keep the image consistent while using higher denoise.
I did a bunch of tests just now and had good results (not sure if I'll post because I just did the start screen background image like 40 times with different parameters).
What could also help is to train your own embedding or Lora of Dee.
But then you will get into trouble whenever it's not only her in the pictures. So batch anything won't work in these cases and you'll be forced to use inpainting for faces or whole characters.
Not to mention that apart from all this, even background will change (slightly or a lot) from picture to picture, same for clothes. Even if you can limit both by using the same seed, it probably won't be enough to make it consistent.
- Mar 16, 2018
- 4,523
- 32,363
Last edited:
- Dec 30, 2017
- 6,961
- 33,607
- Aug 25, 2018
- 185
- 1,474
Dee and Elena testing a new playground