đ Flux-3D-Emojies-LoRA
This is a LoRA model for generating 3D emojies, which can be used in combination with the base model to generate various 3D emoji images.
đ Quick Start
Environment Setup
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-3D-Emojies-LoRA"
trigger_word = "3D Emojies"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Image Generation
You should use 3D Emojies
to trigger the image generation.
⨠Features
- 3D Emoji Generation: Generate a variety of 3D emoji images with different styles and themes.
- Flexible Configuration: Adjust image processing parameters to achieve different generation effects.
đĻ Installation
The weights for this model are available in Safetensors format. You can download them in the Files & versions tab.
đģ Usage Examples
Basic Usage
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-3D-Emojies-LoRA"
trigger_word = "3D Emojies"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
prompt = "3D Emojies, a cheerful orange cat face wearing oversized pink sunglasses with heart-shaped lenses."
image = pipe(prompt).images[0]
image.save("generated_image.png")
đ Documentation
Model Description

Image Processing Parameters
Parameter |
Value |
Parameter |
Value |
LR Scheduler |
constant |
Noise Offset |
0.03 |
Optimizer |
AdamW |
Multires Noise Discount |
0.1 |
Network Dim |
64 |
Multires Noise Iterations |
10 |
Network Alpha |
32 |
Repeat & Steps |
24 & 3250 |
Epoch |
18 |
Save Every N Epochs |
1 |
Labeling: florence2 - en(natural language & English)
Total Images Used for Training: 24 [ Flat 4K ]
Best Dimensions & Inference
Dimensions |
Aspect Ratio |
Recommendation |
1280 x 832 |
3:2 |
Best |
1024 x 1024 |
1:1 |
Default |
Inference Range
- Recommended Inference Steps: 30â35
Trigger Words
You should use 3D Emojies
to trigger the image generation.
Download Model
Weights for this model are available in Safetensors format. Download them in the Files & versions tab.
Technical Details
- Model Type: LoRA for image generation
- Training Data: 24 images in flat 4K resolution
- Labeling Method: florence2 - en (natural language & English)
Property |
Details |
Model Type |
LoRA for image generation |
Training Data |
24 images in flat 4K resolution |
Labeling Method |
florence2 - en (natural language & English) |
License
This model is licensed under the creativeml - openrail - m
license.
đ License
This model is licensed under the creativeml - openrail - m
license.