Sign up for free and get 10,000 credits instantly

Starter credits for new creators, added to your account on the day you sign up.

Server Maintenance Complete — Server maintenance is now complete, and generation speeds for SDXL and Tsubaki.1 tasks are back to normal. Tasks that we…

View details

SD

AnimeNAIV3StyleMIX(模拟NAIV3动漫风格)

AnimeNAIV3StyleMIX(模拟NAIV3动漫风格) - AI Model cover image
อัปโหลดเมื่อ
13 มี.ค. 2567 22:52
การใช้งาน
4.1k
รีวิว
พอใช้ได้  (1)
สิทธิ์
  • Allow image generation & sharing
  • อนุญาตให้ผู้ใช้ดาวน์โหลดโมเดลของคุณ
  • เชิงพาณิชย์

Recommended LoRAs

คำอธิบาย

recommended parameters:Steps: 16, Sampler: DPM++ 2M Karras, CFG scale: 7,or Steps: 23, Sampler: Euler, CFG scale: 7.Size: 512x792.Hires upscaler: Latent (nearest-exact),Denoising strength: 0.6.cuteVersion1:挑取了自己NAI3中手脚不崩坏的图,再分层融合了手脚相对正常的模型所产生的版本,尽可能保留了原有的上色风格。但由于要挑选正常的图片,导致这个版本的训练图片数目还不足,所以在某些场景下的泛化能力应该会很差。Selected images with intact hands and feet from NAI V3, and then used Merging Block Weights to fuse versions generated by models with relatively normal limbs, attempting to preserve the original coloring style as much as possible. However, due to the need to select normal images, the number of training images for this version is insufficient, so the generalization ability in certain scenarios may be poor.

คอมเมนต์

ผลงานโดย AnimeNAIV3StyleMIX(模拟NAIV3动漫风格)