Welcome to Perfection Realistic!
This is an Illustrious XL merge with a bunch of hand-selected checkpoints and LoRAs to improve the base model's realistic capabilites.
And wow, does it deliver!
Also available on mage.space.
It's focus is on creating high quality, photorealistic, but slightly exaggerated images with a focus on women.
Do not use the Normal scheduler. Use Simple or Beta!
Use euler_a, dpmpp_2m_sde or dpmpp_3m_sde as your sampler.
To use the faster low-step settings, you need to use the DMD2 LoRA. This allows you to use 8 or 16 steps and generate very fast. Remember to generate in 2 passes, either using "Hires fix" in Forge/A1111, or by creating and chaining a second sampler node in ComfyUI. A sample workflow if included in the sample images of the model. Use this as a reference.
Each sample/preview image contains the used workflow. Here's a quick article with simpler more beginner-friendly workflow. This is a recommended starting point.
Recommended Settings
Base Generation
Steps: 24
CFG-scale: 4
Sampler: DPM++ 3M SDE
Scheduler: Simple (beta upscale scheduler)
Upscale/Refine
Steps: 8
CFG-scale: 6
Sampler: DPM++ SDE (dpmpp_sde)
Scheduler: Beta
Denoise: 0.35
Description
Enhanced with improved skin colors and body datasets for realism and more complex prompting.
~26000 images trained for 24000 steps at a low LR.
FAQ
Comments (6)
Yes this is a great checkpoint....well done, you chose some excellent ingredients. ....whatever they were..
Generates much better results than any "realistic" checkpoint I tried. Wow, great job mate, thanks for the share!
On Variations, it makes uneven and wonky eyes.
Try with closeup in your prompt, make it zoom in more, or use detailer models to regenerate the face in higher resolution. It's a resolution issue.
@6tZ Oh, that does make sense. They changed the resolution rules to burn Buzz more quickly. I lost a few hundred on this kind of thing. I'm using Variations, so I may need a detailer. I can't zoom in or anything.
@Meikofan I see! Yeah I don't quite know how the onsite tools work like this. But if you are remixing my images for example, you won't get the same result, as I'm using different tools and setups. I'm manually upscaling them with specific settings and upscaler models in ComfyUI, to get the results I'm looking for.
The "generic" all-in-one experience on the site cannot be exactly the same.
But yeah, try to get some more close-ups if you're having problems. Sorry for the trouble.
Details
Files
perfectionRealisticILXL_11.safetensors
Mirrors
perfectionRealisticILXL_11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors
perfectionRealisticILXL_v11.safetensors



















