Sign In

DimSum 点心 NoobAI Vpred

61

641

9

Updated: Jul 13, 2025

base model

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

173

0

Reviews

Published

Jul 13, 2025

Base Model

NoobAI

Hash

AutoV2
8D7BF4BEB8
2025 Year of the Snake Contest Participant
sumai's Avatar

sumai

Read the contents below before use.

I have set a moderation on the gallery of this post, so the NSFW content may not appear on this page.

ABOUT THE MODEL


20250713v0.3

Trained on NoobAI-XL V-pred 1.0

The goal is to recreate Japanese and Korean-style girl. The current training is still in the early experimental stage, and there are still many issues.

The model will gradually increase the dataset size within a controlled scope.

Most of showcase images are generated with ADetailer.

Updates

  • The dataset was increased.

  • Improved the stability of portraits and bust shots.

  • Enhanced skin texture.

  • Tags like “realistic,” “photograph,” and “photorealistic” can enhance the sense of realism.

Issues

  • ADetailer is essential for the face; otherwise, it becomes blurry.

  • Full-body and cowboy shots tend to be unstable, often resulting in distortions in limbs and hands.

  • Distorted fingers and limb.

If you encounter any issues while using the model, feel free to leave a comment.

USAGE GUIDE


Requirement

Recommended Tool: Forge

Sample: Euler

CFG: 3~5.5

Hires.fix: Recommended Upscale value is around 1.2~2.0, denoising strength is 0.1~0.2.

Recommended size: 768*1344, 832*1216, 896*1156, 1024*1024, 1344*768, 1216*8

32, 1156*896

If blurriness appears on the face, please use ADetailer to fix it. The recommended denoising strength is 0.1~0.4.


This model's license inherits from NoobAI-XL V-pred 1.0

ARCHIVES


20250526v0.2

Trained on NoobAI-XL V-pred 1.0

Most of showcase images are generated at SDXL native resolution with ADetailer and Upscale with i2i sd sctript: SD upscale.

Updates

  • The dataset was increased.

  • Enhanced depth and lighting.

  • Enhance realism and generalization capabilities.

  • The caption method and training approach have been changed. caption is now generated using Joycaption2 to produce natural language descriptions, followed by manual refinement. The training method has shifted from DreamBooth to full fine-tuning.

Issues

  • The teeth don’t look quite right.

  • ADetailer is essential for the face; otherwise, it becomes blurry.

  • The ‘from side’ angle doesn't perform well in full-body or cowboy shots.

20250513v0.1 WIP

Trained on NoobAI-XL V-pred 1.0

Issues

  • The images still lack depth.

  • ADetailer is essential for the face; otherwise, it becomes blurry.

  • The style tends to easily regress into a 2D style.

  • The color performance is not good enough.