This is my flagship PaSanctuary (SDXL, IllustriousXL). I find it's in line with what the community on Civitai likes producing. It's pretty versatile while also having an artstyle that's unique in image generation. NSFW compatible. Check out my other Checkpoints.
Refer to the version details for Changelog.
V5:
This Checkpoint is trained on the awesome Basemodel NoobAI-XL V1.1.
The only prompt you ever need is this positive prompt:
masterpiece, best quality, newest, absurdres, highres
Default negative Prompt:
worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale
Additional option for Style change are:
• realistic
No need for any additional negatives. Anything else for tag related stuff, see Basemodel NoobAI-XL V1.1.
This model is designed to work with resources trained on NoobAI-XL V1.1. Other SDXL or pony resources may not work.
I also recommend to use the Extension Adetailer.
Settings for generating Images for V5:
• Sampler: Euler a
• Steps: 30
• CFG 6.0
• Base Resolution 1024x1024
Recipe:
Merge to Checkpoint: TCV Style LoRA Restart Illustrious-XL + NoobAI-XL V1.1.
No additional Merge with block weights, adjustment and clip/tenc.
V4:
This Checkpoint is trained on the awesome Basemodel NoobAI-XL V1.1.
The only prompt you ever need is this positive prompt:
masterpiece, best quality, newest, absurdres, highres
Default negative Prompt:
worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale
Additional option for Style change are:
• realistic/ 3d
No need for any additional negatives, except realistic, 3d, if the realism is bleeding in. Putting 3d in negative prompt is mostly enough. Anything else for tag related stuff, see Basemodel Illustrious-XL.
This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work.
I also recommend to use the Extension Adetailer.
Settings for generating Images for V4:
• Sampler: Euler a
• Steps: 24-3