Welcome to Perfection Influencer!
This is an Illustrious XL merge with a bunch of hand-selected checkpoints and LoRAs to improve the base model's realistic capabilites.
This is a special branch-off for cinematic flavor and for when you need your images to be extra juicy and well-lit!
It's focus is on creating high quality, photorealistic but amateur influencer style images with a focus on women. Use as many big breast or duckface prompts as you want.
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: 30
CFG-scale: 3
Sampler: DPM++ 3M SDE
Scheduler: Simple (beta upscale scheduler)
Upscale/Refine
Steps: 16
CFG-scale: 4
Sampler: DPM++ 3M SDE
Scheduler: Simple
Denoise: 0.35
Description
FAQ
Comments (2)
Hey, I like the images you're generating however when looking at your prompts you seem to get way different results than what you're asking for. in one of the prompt you mentioned 'somalian' and you got a blonde white girl? how can you get more concistency into the result?
This is a good question.
The problem here is that this model is so fine-tuned/merged to a point where it has a strong inherit bias.
This is not a good thing, but it is how the outputs are so strong in terms of visuals. This is why the style is so high. You do end up losing flexibility when you do it like this.
In order to "get through" to the model, you need to prompt for high weights, like "a (somalian:1.8) woman", but even this might not work, so then you need to start prompting for skin color and other attributes.
Alternatively, you can start watering down the model by merging it with more controllable base models, but the style will also be lost.