Sign up free, get 10,000 credits

Starter credits added when you sign up.

SDXL

Aozora-XL Vpred

#MILF#Girl
Aozora-XL Vpred - AI Model cover image

Sign up free, get 10,000 credits

Starter credits added when you sign up.

Uploaded at
Aug 18, 2025, 3:28 AM
Uses
110
Reviews
No reviews
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Description

Aozora-XL: A V-Prediction SDXL ModelAozora-XL is a v-prediction model based on NoobAI v-pred, fine-tuned for improved stability and coherence. It uses a custom training script that allows full/partial fine-tuning on a 12GB consumer GPU, such as an RTX 3060. The training script is available on GitHub at Aozora_SDXL_Training for community use.Version 1.5 UpdatesThis version builds on 1.0 by addressing specific issues in the v-prediction setup. It was trained on the v1.0 base to restore vibrant colors and reduce the slight whitewash effect present in earlier releases. Additional fine-tuning focused on fixing common v-prediction problems, such as inconsistencies in scene composition and detail rendering. It used a dataset of ~50,000 images consisting of visual novel and anime content with deep colors, trained for 5 epochs. Settings included:- Base Model: Aozora V0.1- Max Train Steps: 250000- Gradient Accumulation Steps: 64- Mixed Precision: bfloat16- UNET Learning Rate: 8e-07- LR Scheduler: Cosine with 10% warmup- Features: Min-SNR Gamma (corrected variant, gamma 5.0), Zero Terminal SNR, IP Noise Gamma (0.1), Residual Shifting, Conditional Dropout (prob 0.1)These changes result in better color fidelity and more reliable outputs across various prompts.Version 1.0 OverviewThe initial release (v0.1 alpha) was a proof-of-concept, trained for 10 epochs on a dataset of ~18,500 images (50% ZZZ characters up to version 2.0, 50% top-rated Danbooru images). It maintains traits from the base model (NoobAI-XL/NAI-XL V-Pred 1.0) while showing gains in stability due to the training approach.Project Goals- Provide a GUI-based training script to enable SDXL fine-tuning on consumer hardware.- Continue developing Aozora-XL into a stable, controllable model through ongoing training on diverse datasets.Training MethodThe method optimizes efficiency by training ~92% of the UNet. It includes adaptive Min-SNR gamma weighting for v-prediction stability and custom learning rate schedules.Training Specs:- Hardware: 1x NVIDIA RTX 3060 (12GB VRAM usage: ~11.8 GB)- Optimizer: Adafactor- Batch Size: 1 with 64 Gradient Accumulation Steps- UNet Params Trained: 2.3BRecommended Settings- Positive Prompt: very awa, masterpiece, best quality- Negative Prompt: Optional; try (worst quality, low quality) if needed- Sampler: DPM++ 3M SDE GPU or Euler (Euler for line art, SDE for details like hands/feet)- Scheduler: SGM Uniform or Normal- Steps: 25-35- CFG Scale: 3-5 (works well at low values)- Resolution: 1024x1024 or similar (up to 1152x1152)- Hires. Fix: Use with upscalers like RealESRGEN at ~0.35 denoiseExperiment with settings, as v-prediction models can vary by system.LicenseThis model follows the license of its base, NoobAI-XL. Review and comply with those terms.

Comments

Artwork made by Aozora-XL Vpred