Read the contents below before use.

Trigger word and usage guide are listed below.

ABOUT THE MODEL

Scarlet from Stellar Blade

20250903v0.1

Trained on Chroma v1.0 HD

At present, the characters’ facial features and clothing are almost perfectly reproduced 1:1. However, the model shows no signs of having learned the concept of movement from the dataset.

I think the reasons are:

1. The captions are still too much in the booru-tag style, which prevents Chroma from correctly learning and recognizing them.

2. The captions are not detailed enough.

In addition, the more detailed the prompts for Chroma, the better the results.

All sample images were generated with hire.fx, with an upscaling value of about 1.3x.

Issues

• When the face becomes blurry, consider using Hire.fx to fix it.

• When there is a style deviation, use the "3d" tag for control.

TRIGGER WORDS

All trigger words are based on full body, you can modify them as needed.

Example

You could find the example prompts from my showcase.

My prompts are basically composed in the order of [character traits] + [clothing] + [customize content] + [background], and you can delete or modify them as needed.

Default Outfit

sc213t, a photo of sc213t, a woman,, with silver hair, long hair, bangs, sidelocks, large hat, gold hairpin, brown eyes, she is wearing white leotard, shoulder armor, black shoulder belt, arm guards, armor skirt, white thigh boots

USAGE GUIDE

Requirement

Checkpoints: Chroma v1.0 HD

Recommended Generation Tools: ComfyUI, Forge

Recommended size: 768*1344, 832*1216, 896*1156, 1024*1024, 1344*768, 1216*8

32, 1156*896

I’ve set the gallery moderation of this post to “R”, so explicit content may not appear on this page