- Dec 31, 2016
- 316
- 708
For those that's been avoiding updating their nvidia drivers due to not wanting to deal with the potential usage of shared memory:
You must be registered to see the links
- Dec 31, 2016
- 316
- 708
Which of these do ppl prefer/find the best/least bad? and short note on why if possible.
Something along the process for 2 of the images has removed a strain of hair but left half the shadow which has made a somewhat interesting "running makeup" effect which is not intentional. Fixing it will literally that hours to do just to generate the images so try to ignore that fault.
(I'll update the post with the base prompt later as atm i don't want that to influence things in some way.)
Something along the process for 2 of the images has removed a strain of hair but left half the shadow which has made a somewhat interesting "running makeup" effect which is not intentional. Fixing it will literally that hours to do just to generate the images so try to ignore that fault.
(I'll update the post with the base prompt later as atm i don't want that to influence things in some way.)
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
- Sep 15, 2021
- 1,056
- 4,041
I'd personally say #4 - although the lighting is a little more stark resulting in darker shadows, the 'modeling'* it produces is more subtle and much more realistic.
*I think I'm using that correctly, it's a photography term I seem to have picked up from 'reading' my Dad's books about photography as a teenager, especially the glamour sections...
- Mar 3, 2019
- 239
- 784
#1 and #2 have a warmer color tone to the overall image, which I think fits the image better, and out of those I think that #2 doesn't crunch the blacks as much. But I still like the face definition of #1 better -- on this one she is looking straight at the camera, while #2 she's looking slightly off to the right. So I'd pick #1.
But that's very nitpicky, they all seem very similar.
Is it possible to train a Lora model for a room? Like for instance, you have a room with images taken from different angles. You get several of the couch, the TV, the windows, etc. Then you use that Lora to place a character into that room. For instance, you have someone sit on the couch that was trained in the Lora.
- Aug 24, 2022
- 258
- 666
Yes.. I've experimented with perspective training and actually had really good results.
As long as you don't overcook your train, the diffuser will understand the perspective your giving it then take over with the art style / context you want. This is the perfect use case for a LORA.
(although you can sometimes accomplish this with depth maps instead, as a sort of lazy way.. but I think that's too biased)
If you just want to train a lora for a face you can skip the Lora part and use ReActor, I've had some amazing results replicating people.
You must be registered to see the links
- May 18, 2018
- 214
- 2,152
Does anyone know how to upscale an AnimateDiff gif???
Last edited:
You probably just need to get the gif into an image sequence and then upscale each frame.
Hello, quick question, does anyone know a check point that works well for anime/hassaku style sex scenes. I'm struggling to get multiple characters to appear and finding it impossible to create penetrative sex scenes. It's like i'm stuck in a sfw mode(albeit with tits and vaginas). I'm currently leveraging hassaku hentai model, zedmixhentai and chilloutmix.
Are you trying to use LORAs? Civiti has a tone of sex position Loras. You might be able to get something workable, although when it comes to two or more characters interacting SD can be really hit or miss, especially if you ahve a specific idea.
alternately, find a screen grab of a position you want and use img2img and inpaint to make it work.
alternately, find a screen grab of a position you want and use img2img and inpaint to make it work.
Wow, she looks stunning.
But links are dead, could you reshare it?
And maybe you could do her as HS2 chara.
I do comic work
I have a problem when image is a zoom in shot
event if my model and all lora is 2d stylelish
when go face shot head shot with controlnet
it will add more realistic in it
all promt are the same with very difference outcome
I have a problem when image is a zoom in shot
event if my model and all lora is 2d stylelish
when go face shot head shot with controlnet
it will add more realistic in it
all promt are the same with very difference outcome
- Jan 24, 2020
- 1,401
- 3,805
I'm not doing HS2 content anymore unfortunately but I will upload my Lora again.
Kendra
You must be registered to see the links
- Dec 21, 2020
- 1,580
- 3,796
- Sep 15, 2021
- 1,056
- 4,041
There's an excellent article on
Effectively, an Embedding is "Here's how you draw Cameron Diaz, based on the information you already have" and a LoRA is "Here's the extra data that tells you what Cameron Diaz looks like". Subtly different concepts.
Combining the two is the genius part - you're effectively asking SD to draw Cameron Diaz* as it would normally but with pictures to copy from.
Examples:
*Other attractive female celebrities exist. Apparently.
You must be registered to see the links
about creating Embeddings, but it also includes the advice to combine them with a LoRA/Lycoris/LoCon, but not use the LoRA's trigger word.Effectively, an Embedding is "Here's how you draw Cameron Diaz, based on the information you already have" and a LoRA is "Here's the extra data that tells you what Cameron Diaz looks like". Subtly different concepts.
Combining the two is the genius part - you're effectively asking SD to draw Cameron Diaz* as it would normally but with pictures to copy from.
Examples:
You don't have permission to view the spoiler content.
Log in or register now.
*Other attractive female celebrities exist. Apparently.