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
More contrast
More brightness
Better colors
Better realism
FAQ
Comments (15)
Anyone using Fooocus get it to work right? Its not as good as whats shown here, still works following the sampling methods but not as good with some graphical glitches
yes by following the recommended config manually
Also lowering guidance scale to 1 seems to help
I haven't tried it with Fooocus. I'll check it out when I have time.
best for daily, all works, use simple negative or without. Also steps up to 12, Guidance Scale up to 1.2. And try to clip skip between 1 and 4. Magnifique results!
i've never got really good results out of foocus, plus the upscaling it uses completely destroys fine detail on sdxl models. give swarmui a try instead.
@mariedoll123 this model is not destroyed with upscaling, i'm shocked, really, they are a little bit slightly contrast ones, but better than others models
@ArtdeO no i meant foocus's upscale model in general, juggernaut itself is great . I'm using it on swarmui and posted a few pix with it . upscaling in swarm does a much better job as you can choose the upscale model you want to use. in foocus your stuck with their choice , and you cant use another upscaler in it as its basically wired into the coding.
@mariedoll123
maybe it's still possible, without code, like I did with canny, openpose etc, changing the focus capabilities for the better. But thanks for the tip ;)
Are you using the DMD2 LoRA? Because at least for me I don't have to use it with this model. If I use it I get glitches too.
I've got a v.2.2ALT version and used that. I can't find it any more and the images I posted here are not shown ...
The 2.2 Alt version is version 2.1.
It seems that v2.1 has substantially decreased prompt adherence compared to v2. However, it does offer more contrast, brightness, colors, and a strong tendency towards realism.
Yes, that's likely. I'll release a V2.2 with better prompt adherence.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.