Creator: Arthemy
Hello folks - a big revolution comes with v2.0
v1.0 is still a Checkpoint merge, but the new version is something else entirely.
I've build a custom suite of custom nodes for ComfyUI with the objective of having more granular control over the single weight and values of the model - and I've done what it would be achieved with a checkpoint training by manually rebalancing each weight both in the model, the CLIP and the VAE in order to reach maximum prompt adherence and precision.
You won't be disappointed!
✦ Arthemy Western Art - Quick Start ✦
1_____Size: Around 1024 x 1344
2_____Prompt: Start from the prompts present here and tune the keywords based on your needs:
Quick Prompt
best quality, absurdres, dynamic pose, solo, (toon /(style/)) or best quality, absurdres, dynamic pose, solo, (western comics /(style/))
Quick Negative Prompt
low quality, worst quality, jpeg artifacts, (no_lineart), fisheye
3_____CFG: 3.5
4_____Sampler: Euler a
5_____Steps: 25 to 50





