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
Version 3.4 came out quickly due to the issues with faces in 3.3. I also took the opportunity to improve a few other things. Have fun !
FAQ
Comments (14)
It's been a few days and you're updating again?? Oh my
"Version 3.4 came out quickly due to the issues with faces in 3.3. I also took the opportunity to improve a few other things. Have fun !"
Хорошая турбо модель!!! 9\10
what?? a 9 out of 10 in the Gaussidorovscore!!! this is unprecedented!!!
I truly enjoy working with this model — she is inspiring! The bokeh effect in the photos adds a soft and dreamy atmosphere, enhancing the depth and emotion of each shot. There’s a distinct artistic touch in her presence, almost like visual poetry. I wholeheartedly recommend this model for creative projects and portrait work. She's a perfect choice for those who appreciate beauty, nuance, and expressive storytelling through photography. ❤️
Hey Enzino...I love your models, but is there a particular VAE associated with this model? Did it change from v2 to v3?
I am having that problem where everything looks great until the very end of image generation at which point all the colors shift and the people get a bit uglier.
VAE is backed.
Right...OK...can I ask you this then. What else might have changed from your v2 to v3? I get great color correct images out of your v2 models, but since v3 I get a weird color cast and the people look a little strange. Thanks Enzino...I appreciate your work.
Kid_Glitch_63 No difference on my end, and I haven’t had any feedback about it from the testers. Are you using Forge or ComfyUI?
One of the best realistic xl model.
Feedback: As far as i tested, i noticed 3 finger issue in V3.4.
I'm not the most technologically savvy but it seems into realism doesn't work on forge? It worked on a1111, and all other models I've tried DO work on forge. Any suggestions? I played around with settings to no avail
it's just producing a plain black image
I'm actually working on Forge and it's working. There must be an issue with your settings.
I have a script made with the help of AI to generate images with diffusores: And this last one the 3.4 model for myself trying with several different samplers, the ability to interpret actions, genres, deformations in fingers, it seems that it is inferior to the previous models to the last 2 models I refer to, because the previous ones for my script is limited GPU 1080ti at least, are the best NSFW generators for me using LCM 12: Steps, CFG:1, I just get a lot of similar faces, and Asian content even more clones heheehe, but for me this model is too great, maybe I have to improve something in my script plus the limitation of 77 tokens I can't get around even knowing that XL has 256 token limits, Even so, thank you for the templates.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.