NOTE: To view all gallery images turn off X/XXX browsing level

Main prompt tags: 97bxhxstyle, 1boy <------ should always be included

Recommended samplers:
- Euler Ancestral Scheduler: Normal CFG: 3.0-4.5 Steps: 10-20 Lora strength: 1.0

Prompt tips (green - positive, red - negative):
- brown eyes / red eyes / yellow eyes etc. - main eye style
- bright pupils - second eye style
- simple eyes - third eye style
- circle eyebrows - oval version of eyebrows
- blush stickers - alternative blush style
- 1boy - recommended to include this as a lot of the images were trained on this tag
- furry - will help with anthro characters
- greyscale, sketch, monochrome - just to filter out any potential black and white images

The LoRa should support all kinds of Illustrious checkpoints. Tested working well with the following:

• WAI-NSFW-illustrious-SDXL v12.0 / v14.0

• Plant Milk - Flax

The style will work well with anime characters at 1.0 strength. For cartoon characters its hit or miss - if the style doesn't get applied right away then lower the weight of your character lora.

To improve details:
- generate using higher base resolution (e.g. 1216x1216) or use latent upscaling / highres fix - especially when trying to do full body poses
- for fixing wonky face/eyes I use FaceDetailer node (comfyui) + Adetailer Face finder model

Last image in the gallery can be imported into ComfyUI with a basic workflow:
The image can only be viewed if you disable X/XXX browsing levels.

Requires download of FaceDetailer custom nodes + Eyeful_v2-Paired.pt + FacesV1.pt models (can be Googled). Workflow includes a HiresFix pass with x1.20 latent upscaling by default.
For portraits/upper body shots I recommend lowering the upscaling ratio ('Upscale Latent By' node) - otherwise you might get distorted details.