About this version
After a long time I'm back, a lot of work in the real world and a lot of AI testing, I've been testing several of my models but I decided to go back with the basics, realism realism realism, the attempt to create a realistic model was what took me to start sharing my work, I tried to go back to the basics a little but at the same time have much more advanced things, I think I have reached a level of realism higher than my previous works, I improved a lot in the versatility of the ethnicities and much better attachment at the prompt, I hope you enjoy it
The VAE is not baked, use SDXL_vae
Clip skip: 1
Upscaler: Im using 4x_NMKD-Siax_200k, upscale 1.5 Steps 10 denois 0.35
Width and height: 896*1152
CFG Scale: 5
Steps: 35
The sampling method i use is DPM++2M SDE Karras but try with others if you want, i get excellent results with KL Optimal and Polyexponential
OLDER versions
In this model I wanted to absolutely focus on trying to create the most realistic images possible, I left the details to my other models so that in this one we can get as close to reality as possible
This model was made out of my obsession with realistic pony models, the intention is to create a model that can be compared to the reality of the XL, I hope to see your creations and please be respectful of the community, The examples I made were made with the DPM++2M SDE Karras sampling method with 35 steps and denois 5, the size 896x1152, the Hires.fix with the 4x_NMKD-Siax_200k upscaler with 10 steps, scaled to 1.5 and denoising 0.35, feel free to try other configurations
Description
This is version 2 of my first model, with many improvements especially in understanding the prompt, colors, textures and with BakedVae, as always 100% focused on realism, my main recommendations are to try to keep the prompt short and it is not necessary to use negatives unless you consider it very necessary, all the examples were made without the use of Loras to try to show the capabilities of the model
FAQ
Comments (10)
Does this version still need no score strings in the prompt?
This model need the score parameters for better images, for No Score yo need my other model, this one is for.more realistic and the other is realistic but more detailed
Can you share your specs of resolution, CFG, sampler and if you can share and example please
@Sateluco
score_9, score_8_up, score_7_up, BREAK photo (medium) , (realistic:1.2), realistic, photo, aesthetic erotic photography, 1girl, souryuu asuka langley, blue eyes, blush, solo, medium breasts, hairpods, red hoodie, long sleeves, claw pose, looking at viewer, smile,
Steps: 20, Sampler: DPM++ 2M SDE Karras, CFG scale: 4.5, Seed: 588197850, Size: 800x1200, Model hash: 2d5ffd59c1, Model: satpony_v10, Version: f0.0.9-latest-51-g5bea443d
here is a link to an example
https://civitai.com/images/18984488
I marked these places
@sdneng951 i made an image with the exact parameters you put, i dont see the artifacts, im using Forge, maybe has to be another thing Image post by Sateluco | Civitai
@Sateluco I also work through Forge. I also tried using ComfyUi, the same result.
@Sateluco such artifacts are obtained only with your model.
@sdneng951 Seems to be a VAE thing. I'm running it locally with invoke-ai and had the same issue until I changed to an FP16 VAE.
I love the PONY models. But I wish they can get updated with humans from more races like Indian, and East Asian with various skin tones and facial features.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.