Koshi Torako 虎視 虎子 PONY - Shikanoko Nokonoko Koshitantan / My Deer friend Nokotan
Anime still ongoing it is the first episode.
Will update with more training data when it is available..
Trigger word(s): ctiank0shi, blonde hair
Clothing: serafuku, sailor collar, blue neckerchief, skirt, long sleeves,
commission: https://ko-fi.com/ctian 😼
Example
Positive prompt ✅:
score_9, score_8_up, score_7_up, source_anime, masterpiece, 1girl, ctiank0shi, blonde hair, serafuku, sailor collar, blue neckerchief, skirt, long sleeves, looking at viewer, outdoors, sunny, city, depth of field, 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
FAQ:
Q: why not use character name as trigger word?
A: I use unique token to prevent other things from being prompted when using triggerword
Q: do you have other account in other websites?
A: yes, tensor, pixai
Q: what external generator do you use?
A: a111 mostly, comfyui for img2vid
