Find all my models, scripts, and beta versions on my Ko-Fi.
☄️ IntoRealism
IntoRealism is a model designed for high-fidelity realism. From lifelike portraits to nuanced lighting and natural textures, this model brings your prompts to life with stunning detail, without sacrificing flexibility or creative control.
📢 Join The Community
We're building a friendly space to chat, share creations, and get support.
👉 Click here to join the Discord
You can visit my Ko-fi page if you appreciate my work for a small donation, orders, etc.
⚡ DMD2 Usage
Sampling method: LCM / Exponential or Karras for V3.5
Sampling steps: 8 to 12
Resolution: 896x1152 / 832x1216
CFG: 1Upscaler
4x-UltraSharp or others
Denoising strength : 0.3
Hires CFG Scale : 1Adetailer
Adetailer model: face_yolov9c.pt
Inpaint denoising strength : 0.25 or 0.30SDXL Usage
Sampling method: DPM++ 2M SDE Karras
Sampling steps: > 25
Resolution: 896x1152 / 832x1216
CFG: 4-5Upscaler
4x_NMKD-Siax_200k or other
Hires steps : 4
Denoising strength : 0.3
Hires CFG Scale : 4Adetailer
Adetailer model: face_yolov9c.pt
Inpaint denoising strength : 0.4 (long view)ZIT Usage
Sampling method: Euler / Beta
Sampling steps: 6/10
Resolution: 896x1152 / 832x1216
CFG: 1Description
Even more realism
More natural faces
More realistic photos
FAQ
Comments (6)
Just one thing, though it understands very well the prompts it doesnt play very well with LoRas
Which LoRAs ? Can you give me some examples ?
I just realized this model gives every single output pubic hair if they're naked.
It cannot do shaved, which is really annoying.
This was my test prompt
"A closeup front on view of a naked slender woman's shaved hairless pelvis and genital area with wet skin, she stands outside in the dark light.
There is a golden softbox light from below which is the only light in the scene
She has a shaved pubic region, shaved, shaved pubic hair"
I'm no expert, but it could be the sampler and not the model. I use TCD sampler instead of LCM and when I used the first part of your prompt I got the totally bald beaver on a skinny wet woman like you were looking for. Apparently LCM sort of sacrifices accuracy for speed when compared with TCD. Just a thought.
This issue (which was rare on my end) should no longer happen in version 3.3. Version 3.2 pushed realism a bit too far, slightly overlooking prompts and NSFW content.
"She has a shaved pubic region, shaved, shaved pubic hair"
The problem with prompting like this is you have included the tokens "pubic hair". Even though it says shaved, it also says "pubic hair". Might have more luck focusing on putting "pubic hair" in the negative prompt at a high strength, rather than trying to describe that there is "no" something in the positive prompt, which can sometimes have the opposite effect, i.e. you mentioned it, so the model will give it to you.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.