IntoRealism - DMD2 V3

NSFW

You can download V4 BF16 on my Ko-Fi, or sign up for a Pro subscription for $25, which gives you access to all my models, early access, scripts, WF, and more...

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: 1

Upscaler

4x-UltraSharp or others
Denoising strength : 0.3
Hires CFG Scale : 1

Adetailer

Adetailer model: face_yolov9c.pt
Inpaint denoising strength : 0.25 or 0.30

SDXL Usage

Sampling method: DPM++ 2M SDE Karras
Sampling steps: > 25
Resolution: 896x1152 / 832x1216
CFG: 4-5

Upscaler

4x_NMKD-Siax_200k or other
Hires steps : 4
Denoising strength : 0.3
Hires CFG Scale : 4

Adetailer

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: 1

Description

🆕 Version 3 is here with plenty of improvements!
The model is now fully compatible with both NSFW and SFW content.
Landscapes work great and deliver a strong sense of realism — which wasn’t easy to achieve, since DMD2 doesn’t handle that well by default.

👉 Settings remain unchanged, but I recommend using 12 steps for landscapes, animals, and similar scenes to get the best results.

🔜 Version 3.1 is already in the works and should drop later this month. The focus will be on adding more face variety and improving poses for better flexibility and character diversity.

Have fun, always !

FAQ

Comments (6)

liftweightsJun 13, 2025· 1 reaction

CivitAI

Whoa, that was quick! v2.2 was already super impressive, looking forward to seeing what this new one can do.

alullesJun 13, 2025· 1 reaction

CivitAI

Very speedy and responsive to prompts. Great stuff. Thanks for your work. Appreciated.

artishticJun 13, 2025

CivitAI

I tried using your v3.0 model in ComfyUI using SubtleShader's DMD2 workflow but got low quality, semi fuzzy images. I did get it to work in Forge but wish I could make it work in Comfy. I have gotten SubtleShader's ComfyUI workflow to work with the BigLove checkpoint

enzino

Author

Jun 14, 2025

No need for an advanced workflow — a simple + upscale is enough to get a great result.

BuffaloSymphonyJun 15, 2025· 2 reactions

CivitAI

The human subjects are clearly SDXL, but I'm amazed with the scenery and landscapes, I thought some of these were flux or Mid journey

NoMarzipan8994381Jun 20, 2025· 11 reactions

CivitAI

I already wrote a comment, I write another one. This is the best checkpoint ever, the best if you are looking for amateur realism. Before I had a lot of different checkpoints (taking up a lot of space), I deleted them all because nothing can compete with this, maybe only Lustify.. the best SDXL checkpoint ever.

Checkpoint

SDXL 1.0

by enzino

Download (Beta) View on CivitAI