Yangxin Chenさんのイラストまとめ

#stablediffusion #AI #azuki Trained an Azuki model and generated some images of it @Azuki it is already anime style so making it realistic seems to be more fun

#stablediffusion #GenshinImapact It seems I have found the right method of training multi-identifier model: "_"style captioning and smaller filesize. My latest model of Barbara works pretty well with the method.

#stablediffusion #HonkaiImpact3rd Forgot to share this Lora model by me: https://t.co/GKRBmzjkf4
This was my biggest breakthrough in training so far, 4 identifier in just one Lora.

#HonkaiImpact3rd #stablediffusion Just released a Lora of Raiden Mei on CivitAI: https://t.co/BuuRafbKhu
Still have issues with multi-entry model, so a simple one for now.

#stablediffusion #HonkaiImpact3rd Try to include all 4 costumes of Elysia into one Lora model, but the result looks not that promising. More tuning are needed😅

#stablediffusion #GenshinImpact Another Lora model of Sangonomiya Kokomiby me: https://t.co/gCgdi83Srw trained by the 5+5 method. So 5+5 is half validated.

#stablediffusion #GenshinImpact my first trained well-working LoRa model: https://t.co/DuRrpKPxCX It was the first time to find the 5+5 LoRa training method on this model. Two costumes of Ningguang were merged into one Lora.
And most importantly, the face is so official!