Updated: Jul 6, 2024
character
IMPORTANT: READ BELOW
Trigger word(s): ctianm4rs, red hair,
Clothing: bodysuit, white short dress,
commission: https://ko-fi.com/ctian 😼
Example
Positive prompt ✅:
score_9, score_8_up, score_7_up, source_anime, masterpiece, 1girl, red hair, ctianm4rs, bodysuit, white short dress, outdoors, city, depth of field, looking at viewer, sitting, hand on own face, shaded face, evil grin, Negative prompt ❌:
score_4, score_5, score_6, source_cartoon, source_furry, source_pony, sketch, 3d, painting, monochrome, dust particles, full body,Recommended resolution, aspect ratio for sdxl, pony 📷
768 x 1344: Vertical (9:16)
832 x 1216: Portrait (4:5) **
1024 x 1024: Square (1:1)
1182 x 886: Photo (4:3)
1254 x 836: Landscape (3:2)
1365 x 768: Widescreen (16:9)
Work flow, procedure 🔧
1. Collect dataset (booru, anime screencaps, search)
2. Clean up dataset using upscalers, inpainting and photoshop
3. Tag dataset using booru github
4. Train LoRa in kohya ss locally github
5. Test epochs using xyz grid in controlnet to ensure LoRa is not overfitted/underfitted.
6. Submit model to CivitAI profile
do not ask me training parameters, check lora metadata for training parameters

