Posted for civitai.com and tensor.art only

Each of these LoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.

-MoC

Veronica Zemanova

Image Generation Suggestions

I generate these images using Mcmonkeyprojects' SwarmUI (a powerful but easy to use front end for ComfyUI). I find Forge results lacklustre at present.

Core Parameters
Model: Flux1-dev with clip_l, t5xxl_fp16.
Steps: 30
CFG Scale: 1

Sampling

I've had success with a good amount of samplers and schedulers, but at present am using the following,
Sampler: DEIS
Scheduler: Beta
Flux Guidance Scale: 3.5

Prompt
With SwarmUI use the <Segment:> feature to inpaint particular portions of the output. This can be nearly anything the segment model used was trained on, face, eyes, feet, top, etc.

A general statement I tag to most of these prompts is:
<segment:face,0.7>Imagine a real life highly grainy 35mm photograph of MoCModel face with incredibly lifelike intricately detailed eyes