CivitAI Style Fusion🏆LoRAs
Last update: 🚀 CivitAI Lora5 32DIM Notebook with dataset
Last update: 🚀 CivitAI Lora3 Configuration - Trained with CivitAI Trainer
🚀 Date: 2023-11-10 | Title: CivitAI_64_ALL
🔍 Key Specifications:
Resolution: 1024x1024
Architecture: stable-diffusion-xl-v1-base/lora
Network Dim/Rank: 64.0, Alpha: 1.0
Module: networks.lora
Learning Rates: UNet LR & TE LR set to optimal levels
Optimizer: Advanced AdamW8bit
Epochs & Training: Intensive 10 epochs with 576 batches
📊 Model Stats:
Resolution: 1024x1024 Architecture: stable-diffusion-xl-v1-base/lora
Network Dim/Rank: 64.0 Alpha: 1.0
Module: networks.lora
Learning Rate (LR): 0.0005 UNet LR: 0.0005 TE LR: 5e-05
Optimizer: bitsandbytes.optim.adamw.AdamW8bit(weight_decay=0.1)
Scheduler: constant Warmup steps: 0
Epoch: 10 Batches per epoch: 576 Gradient accumulation steps: 1
Train images: 2304 Regularization images: 0
Multires noise iterations: 6.0 Multires noise discount: 0.3
Min SNR gamma: 5.0 Zero terminal SNR: True Max grad norm: 1.0 Clip skip: 1
Dataset dirs: 1
[img] 576 images
UNet weight average magnitude: 7.602270778898858
UNet weight average strength: 0.018722912685324843
Text Encoder (1) weight average magnitude: 2.7649271326702607
Text Encoder (1) weight average strength: 0.009535635958680934
Text Encoder (2) weight average magnitude: 2.6905091182810352
Text Encoder (2) weight average strength: 0.007233532415344915
Delve into FFusionAI's approach to AI-driven style synthesis with our newly released LoRA models. Each model has been developed using CivitAI's official trainer, ensuring precision and quality.
🛠️ LoRA Model Overview:
LoRA 1 - Lite Version: Designed for quick testing, this model utilizes a small dataset for swift style generation, operating with a 32-dimension capacity.
LoRA 2 - Community Fusion: A robust model developed from over 500+ images, submitted by various users for the CivitAI contest. This iteration also features a 32-dimension capacity.
LoRA 3 - Enhanced Fidelity: Building upon LoRA 2, this model is further trained with higher dimensions, focusing on improving the overall image quality.
LoRA 4 - Comprehensive Style Mash: Our expansive dataset of 1400 images represents a confluence of all FFusionAI submissions. This model undergoes additional UNet training to refine and diversify the generated styles.
1. FFusionAI Style Capture & Fusion Showdown LoRA
🎨 Dataset and Training:
Included within the package are curated collections accessible at CivitAI Collections. The training prompts have been crafted with BLIP-2, FLAN-T5-XL, and ViT-H-14.
Please note, original prompts were not utilized for training. Instead, intentional modifications were made using blip2-flan-t5-xl & ViT-H-14/laion2b_s32b_b79k to adjust and enhance the training dataset, which can be reviewed here.
🔄 Further Information:
For a detailed examination of the training datasets, parameters, and model specifications, professionals and enthusiasts are encouraged to explore the metadata provided within the collection.
🚀 Trained with the Official CivitAI Trainer
📅 Date: 2023-11-10
🖼️ Title: CivitAI_ALL
🔍 Resolution: 1024x1024
🏗️ Architecture: stable-diffusion-xl-v1-base/lora
⚙️ Key Settings:
Network Dim/Rank: 32.0
Alpha: 1.0
Module: networks.lora
Learning Rates: UNet LR - 0.0005, TE LR - 5e-05
Optimizer: AdamW8bit (weight_decay=0.1)
Epochs & Batches: 10 epochs, 167 batches/epoch
Train Images: 576
📊 Model Stats:
UNet Weight: Mag - 3.755, Str - 0.0135
Text Encoder (1): Mag - 1.833, Str - 0.0091
Text Encoder (2): Mag - 1.836, Str - 0.0071
🏷️ Prominent Tags:
Fusion styles, Artgerm, Beeple
Dark fantasy, Official artwork, Pinup art
Digital illustration, Fantasy & Sci-fi
...and over 4500 more!
🌐 FFusion.ai Contact Information
Proudly maintained by Source Code Bulgaria Ltd & Black Swan Technologies.
📧 For collaborations, inquiries, or support: [email protected]
🌍 Locations: Sofia | Istanbul | London
Connect with Us:
Our Websites:
