Since SDXL is right around the corner, let's say it is the final version for now since I put a lot effort into it and probably cannot do much more.
I tried to refine the understanding of the Prompts, Hands and of course the Realism.
Let's see what you guys can do with it.
Thanks to @drawaline for the in-depth review, so i'd like to give some advices to use this model.
[expand to see Advices]
use simple prompts
no need to use keywords like "masterpiece, best quality, 8k, intricate, high detail" or "(extremely detailed face), (extremely detailed hands), (extremely detailed hair)" since it doesn't produce appreciable change
use simple negatives or small negative embeddings. gives most realistic look (check samples to get an idea of negatives i used)
add "asian, chinese" to negative if you're looking for ethnicities other than Asian
Light, shadows, and details are excellent without extra keywords
If you're looking for a natural effect, avoid "cinematic"
avoid using "1girl" since it pushes things to render/anime style
to much description of the face will turn out bad mostly
for a more fantasy like output use 2M Karras Sampler
no extra noise-offset needed, but u can if you like to π
Prompt: simple explanation of the image (try first without extra keywords)
Negative: "cartoon, painting, illustration, (worst quality, low quality, normal quality:2)"
Steps: >20 (if image has errors or artefacts use higher Steps)
CFG Scale: 5 (higher config scale can lose realism, depends on prompt, sampler and Steps)
Sampler: Any Sampler (SDE, DPM-Sampler will result in more realism)
Size: 512x768 or 768x512
Hires upscaler: 4x_NMKD-Superscale-SP_178000_G (Denoising: 0.35, Upscale: 2x)
!After Detailer | ControlNet | Agent Scheduler | Ultimate SD Upscale
β No VAE needed but it is better to use one for more vibrant colors
β Feel free to leave Reviews and Samples - and always have fun creating β€
epiCRealism is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user epinikion. Derived from the powerful Stable Diffusion (SD 1.5) model, epiCRealism has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that epiCRealism is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as photorealistic, female, analog.
With a rating of 4.89 and over 1999 ratings, epiCRealism is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of epiCRealism from here.
To use epiCRealism, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion β it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like epiCRealism, check out our crash course in AI image generation.
Since i'm low on time i still wanted to release the RC1 of an new aproach.
ordinary faces, natural look, more face diversity
hand fix
VAE included
Recommended simple Negative for average looking output, avoid "optimizer" Embeddings
cartoon, cgi, render, illustration, painting, drawing
seems to be a bit nsfw heavy and very lose on prompt guidance for now