Type | |
Stats | 667 1,405 |
Reviews | (107) |
Published | Jun 25, 2024 |
Base Model | |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | ctiank0nek0, dress shirt, pleated skirt, black ribbon, red skirt, half black uniform, |
Hash | AutoV2 B891E69DBE |
IMPORTANT: READ BELOW
please use weight 1 when using main clothing
Trigger word(s): ctiank0nek0,
Clothing: dress shirt, pleated skirt, black ribbon, red skirt, half black uniform,
Cat: cat ears, cat tail,
commission: https://ko-fi.com/ctian 😼
Example
Positive prompt ✅:
score_9, score_8_up, score_7_up, source_anime, masterpiece, 1girl, ctiank0nek0, dress shirt, pleated skirt, black ribbon, red skirt, half black uniform, long sleeves, outdoors, city, depth of field, looking at viewer, cat ears, cat tail, claw pose, chestnut mouth,
Negative prompt ❌:
sketch, 3d, claws
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