š„ Download IntoRealism SDXL ULTRA V1 on Ko-Fi via credit card or PayPal
OR
# š„ ONE MEMBERSHIP = FULL ACCESS
Your membership includes :
- models
- workflows
- scripts
- Exclusives
- future updates
š $25/month on Ko-Fi
š¢ Join The Community
We're building a friendly space to chat, share creations, and get support.
š Click here to join the Discord
āØ IntoRealism Ultra is an experimental release that combines the strength of DMD2 with the finesse of a Light model, delivering a more realistic look than ever before.
š A rare feature : unlike most light models, negative prompts work perfectly, giving you much more control and precision over the final renders.
š¹ Key features:
DMD2 + Light blend
Enhanced realism (textures, skin, natural lighting)
Handles NSFW content very well
Fully compatible with negative prompts
Versatile: portraits, lifestyle, cinematic scenes
better LoRA adherence
ā ļø Note : this is an early test version. The model will be further optimized and refined in future updates for even greater realism and flexibility.
Usage
Sampling method : Euler A Karras or Exponential
Sampling steps : 6 - 12 (12 - 14 for V6)
Resolution : 896x1152 / 832x1216
CFG : 1.5 - 2
Workflow : https://civarchive.com/models/2383077/intorealism-ultra-workflow
Description
A few minor changes in realism and NSFW.
FAQ
Comments (19)
It's a great model, although I couldn't achieve good image quality with the default settings, but with the LCM model and upscaling, I got results that surpassed any other model. It's also very fastānot a big deal for me, but a deciding factor for many.
Thank you for the suggestion. I was able to make a comfyui workflow for your suggestion. Sharing here with the community https://pastebin.com/aAW5FV7j
@oo7mĀ The workflow is great, but where did you get the scheruler ays?
@davosem70898Ā It's part of the Ksampler in Comfyui. Try updating your comfyui
@oo7mĀ thanks for the reply. I already updated, but it's not there. I guess there's a problem somewhere.
@davosem70898Ā Sampling > Custom Sampling > Schedulers. Add that SamplerCustom. Or Inspire Pack > a1111_compat > KSampler (inspire). That KSampler node has AYS in the Schedulers dropdown.
@theboomguy31289Ā Thanks
10x better that gonzalmo guy , i love u
This is very good. I prefer V7 to V8. The images of v8 are slightly darker in colour.
What is the "Light Blend" you added? Must be a LORA?
I really like the low dmd, I would also like a version with none.
Thanks for your feedback. I'm trying to vary the versions a little. I'm not sure that V8 is much darker, but perhaps the desire to emphasize realism gives that impression. I'll take a closer look at that for V9.
Truly breath taking checkpoint! Can't believe I did not see your's earlier. Any advice on creating characters loras on your model?
Thx ! I recommend using the IntoRealism XL version or models such as CyberRealistic. It works perfectly with the Ultra version. And it is greatly enhanced in realism with Facedetailer or Adetailer.
Train Loras of any type (SD, SDXL, Flux, ZiT, and others) ONLY on the corresponding base models! Only then will they be authentic.
Brilliant model! I try most of them, this is the best I've seen by far. Follow the recommended settings and your gold.
Sorry, but I can not get it working with the embedded workflows - the output is always back. Also I can not find frostbitev2_Illu_dwnsty LoRA...
The sample photos are generated with Forge. So I don't know what this Lora is. For Comfyui, a simple, well-configured WF XL is sufficient.
@enzinoĀ Ok, I will try with Forge. Some of the samples contain ComfyUI workflow, but it only produced black output, until I simplified them, but then the results were not good...
@venziboĀ Civitai must provide fake examples because all examples are generated by Forge.
it's black when you don't use clip skip, (CLIP set last layer -2)