Case-Hardened

Prompt
cinematic film still one man, orc, in armor. shallow depth of field, vignette, highly detailed, high budget Hollywood movie, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy

Prompt
Old tree, A detailed illustration muted chinese ink painting, muted colors, rice paper texture, splash paint, halo ai, one human, one red sun. Venus. Space. Clouds wet to wet techniques. vibrant vector. using Cinema 4D

Prompt
(dynamic lighting:1.1), ((masterpiece)), solo, portrait, Thri Kreen, furry insect, colored sclera, beetle antennae, 2 pairs of hands, 1girl, flat breast, yellow eyes, white chitin, grey shirt, steel armor, fantasy background, blurred background

Model description

CaseH-beta

CaseH does not mean hentai case; instead, CaseH stands for Case Hardened.

It derives from the SDXL distillation, creating a 1.5 model.

Recommended configuration:

Sampler: DPM++ 2M Karras
Steps: 15-55 (recommended 35)
CFG: 2-5 (recommended 4)

The higher the CFG value, the fewer steps should be used.

How

This model represents an idea I have been experimenting with. It seems I've managed to produce a release-worthy version.

Actually, my concept is quite straightforward, based on the following two assumptions:

The model has ample capacity to accommodate more knowledge.
Consistency in architecture implies the possibility of distillation (and we could focus on learning just the realistic part).

Therefore, I attempted to use the SDXL model (one of the more popular versions on Civitai) as the teacher model to distill knowledge into the SD1.5 model (the beta version is based on the LOFIv4 tune-up).

To my surprise, this round of fine-tuning has significantly surpassed previous distillation (raw-xs) versions. After the tune-up, LOFIv4 has almost completely abandoned the asian-style and shifted entirely towards SDXL.

Beta Issues

ti model lora model may not be used as expected Due to the strong leaning towards learning from SDXL, it could cause the action on the 1.5 TI model to fail, such as with the ng_deepnegative_xx series models.