3D Icon Flux LoRA Open-Source Model - Freely Generate Unique-Styled 3D Icon Images

3d Icon Flux LoRA

Developed by rangwani-harsh

This is a DreamBooth LoRA weight trained based on the FLUX.1-dev model, specifically designed for generating 3D icon-style images.

Image Generation Open Source License:Other #3D Icon Generation #Flux Stylization #LoRA Fine-tuning

Downloads 46

Release Time : 10/9/2024

Model Overview

The model is trained using DreamBooth and Flux diffusers trainer, capable of generating images with specific 3D icon styles based on text prompts.

Model Features

3D Icon Style Generation

Capable of generating images with specific 3D icon styles

DreamBooth Fine-tuning

Fine-tuned using DreamBooth technology, adapting to specific styles while preserving the base model's capabilities

LoRA Weights

Utilizes LoRA (Low-Rank Adaptation) method for efficient fine-tuning

Model Capabilities

Text-to-Image Generation

3D Icon Style Transformation

Specific Style Image Generation

Use Cases

Digital Design

3D Icon Design

Quickly generate 3D-style icons for various themes

Examples showcase the generation effect of an astronaut riding a horse icon

Brand Visual Elements

Create consistent brand visual elements and icon systems

Game Development

Game UI Elements

Generate 3D-style icons required for game interfaces

🚀 Flux DreamBooth LoRA - rangwani-harsh/3d-icon-Flux-LoRA

This project offers rangwani-harsh/3d-icon-Flux-LoRA DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev, enabling text-to-image generation with specific styles.

🚀 Quick Start

Download the Model

You can Download the *.safetensors LoRA in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file

pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')

embedding_path = hf_hub_download(repo_id='rangwani-harsh/3d-icon-Flux-LoRA', filename='3d-icon-Flux-LoRA_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)

image = pipeline('a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers.

✨ Features

Model Description

These are rangwani-harsh/3d-icon-Flux-LoRA DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev. The weights were trained using DreamBooth with the Flux diffusers trainer.

Was LoRA for the text encoder enabled? False.
Pivotal tuning was enabled: True.

Trigger Words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept `TOK` → use `<s0><s1>` in your prompt

📚 Documentation

Model Information

Property	Details
Model Type	rangwani-harsh/3d-icon-Flux-LoRA DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev
Training Method	Trained using DreamBooth with the Flux diffusers trainer
Text Encoder LoRA	False
Pivotal Tuning	True

Intended Uses & Limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]

📄 License

Please adhere to the licensing terms as described here.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご