First model merger test I did, credits to the models below.
AbsoluteReality: https://civarchive.com/models/81458?modelVersionId=132760
BeautyFool: https://civarchive.com/models/101888?modelVersionId=134148
realspice: https://civarchive.com/models/158734?modelVersionId=208629
For this model I recommend using some basic prompts like positive and negative.
Positive prompts: masterpiece, high quality, best quality, Detailed
Negative prompts: EasyNegativeV2, low quality, normal quality, worst quality, (bad anatomy)
Other combinations of negative prompts also work, as does using Fastnegative or BadDream (but I strongly recommend using EasynegativeV2, because of all my tests, this is the negative that works best without damaging the image too much in StableDiffusion)
Don't use Embedding NegfeetV2, I don't know why, but it ruins the image if you use this Embedding in this model
Recommended settings
Sampling steps: 15-30 (Only use more steps as a last resort for very complex images, as an excessive number of steps tends to ruin the image)
CFG Scale: 5-12
Hires. Fix
Upscaler: 4xNMKDSuperscale_4xNMKDSuperscale
Hires Steps: 15-20
Denoising Strenght: 0,20-0,40 (The more force, the cleaner the image, but the more the original quality is lost.)
Upscale By: 1,5 - 2,0
Adetailer:
Adetailer Model: face_yolov8n.pt
Inpaint denoising strength: 0,25 - 0,40
ADetailer steps: 15 - 20
Did you like the content? I would be grateful to receive a coffee
https://ko-fi.com/berserkfg
This model is open source for pornography, therefore pornographic images are at the image creators' own risk, and the model will not be held responsible for any image with heinous content.
Description
I made some changes and I think it improved the eyes and colors, and it seems to have more details.
This time I generated all the images without using Lora, my idea was to show the model's capabilities without interference from any Lora.
FAQ
Comments (14)
V1.2 is fantastic
I'm glad you liked it :)
version 1.2. is already working on the civitai generator
Was it taken down? I wanted to give it a try.
i really in love with this model.
I'm glad you like it :)
Could use a bit more variety on the preview images, I almost skipped this gem of a model because I wasn't sure if it could generate men. Alas, for my purposes of turning outputs from photorealistic models into digital art for D&D it works like a charm like how no other model so far did.
I confess that I'm not very good at choosing images kkkk. I'm also a fantasy fan, so much so that I was a D&D master and I still intend to create a Lora focused on this type of content.
HANDS. the thing this model does EXCEPTIONALLY well, is hands. since it's a merge... happen to know the source that got the good hands going?
Honestly, I can't really say which model has good hands, and I would say that the hands weren't even my main focus when it came to the fusion, but rather the eyes. But the hands could have been from the Realspice model
I say it have very bad hands. Especially nails. Nowhere close to AnalogMadness.
This model is awesome!
thanks for the appreciation <3
Your model is amazing at actually doing faces from quite far away. Most models fail miserably at that.
Excellent job.
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.