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

SDXL

NoobAI VPred+IterComp (test)

NoobAI VPred+IterComp (test) - AI Model cover image
อัปโหลดเมื่อ
7 พ.ย. 2567 08:45
การใช้งาน
5.7k
รีวิว
ดี  (3)
ขั้นตอนการสุ่ม

20

ค่า CFG

6

ไม่ต้องการ

blurry, distorted, film grain, grainy, yellow theme, error, worst quality, sketch, signature, monochrome, jpeg artifacts, scan artifacts, compression artifacts, artist name, artist logo, patreon username, watermark, (bad hands:1.3), deformed, (extra finger:1.3), steam, steaming body, sad, frown

สิทธิ์
  • Allow image generation & sharing
  • อนุญาตให้ผู้ใช้ดาวน์โหลดโมเดลของคุณ
  • เชิงพาณิชย์

Recommended LoRAs

คำอธิบาย

This is a stabilization of the v-prediction test of NoobAI. Weights from IterComp are added onto the model using sd_mecha with perpendicular component add difference. (this prevents noise schedule from being affected). Then the original clip is merged into the result.V-prediction support should be in the next version of Automatic1111. In ComfyUI, use the ModelSamplingDiscrete node. In SwarmUI, select "Vpred ZSNR" under "Prediction Type" in "Edit Metadata" on the model.Iterative Composition-Aware Feedback Learning: https://arxiv.org/pdf/2410.07171APG scaling helps with dynamic range.

คอมเมนต์

ผลงานโดย NoobAI VPred+IterComp (test)

1