Castor-3D-Portrait-Flux-LoRA Open Source Model - Generate 3D Cartoon Style Portrait Paintings Based on Text Descriptions

Castor 3D Portrait Flux LoRA

Developed by prithivMLmods

A LoRA fine-tuned 3D portrait cartoon generation model capable of creating cartoon-style portraits with 3D effects based on text descriptions.

Image Generation Open Source License:Openrail #3D Cartoon Portrait Generation #LoRA Fine-tuned Diffusion Model #Highly Expressive Character Rendering

Downloads 1,137

Release Time : 10/29/2024

Model Overview

This model is a LoRA fine-tuned version based on the black-forest-labs/FLUX.1-dev foundation model, specializing in generating 3D cartoon-style portraits. It can produce artistic and dimensional cartoon character portraits from text prompts.

Model Features

3D Cartoon Style

Capable of generating portraits with a sense of depth and cartoon artistic style

LoRA Fine-tuning

Efficient fine-tuning of the base diffusion model using LoRA technology

Detail Control

Control character appearance, pose, clothing, and background details through text prompts

Model Capabilities

Text-to-Image Generation

3D Cartoon-Style Portrait Generation

Character Feature Detail Control

Scene Atmosphere Rendering

Use Cases

Digital Art Creation

Personalized Cartoon Avatars

Generate personalized 3D cartoon-style avatars for users

Produces cartoon-style portraits with user-specific features

Character Design

Quickly generate character concept art for games or animation projects

Creates 3D cartoon-style character images that meet requirements

Social Media Content

Social Media Avatars

Generate unique cartoon-style avatars for social media users

Produces artistic 3D cartoon avatars

Content Creation

Generate accompanying cartoon-style illustrations for blogs or articles

Creates 3D cartoon images matching the content theme

🚀 Castor-3D-Portrait-Flux-LoRA

This is a text-to-image LoRA model based on the black-forest-labs/FLUX.1-dev base model, specializing in generating 3D portrait cartoons. However, the model is still in the training phase, and the current version may have some artifacts and performance issues.

🚀 Quick Start

Installation and 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 = "prithivMLmods/Castor-3D-Portrait-Flux-LoRA"
trigger_word = "3D Portrait"  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger Words

⚠️ Important Note

You should use 3D Portrait to trigger the image generation.

Download Model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

✨ Features

3D Portrait Generation: Specialized in generating 3D portrait cartoons.
Based on LoRA: Utilizes the LoRA technique for efficient fine - tuning.

📦 Installation

The installation steps mainly involve setting up the Python environment and loading the model weights. The specific steps are as follows:

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 = "prithivMLmods/Castor-3D-Portrait-Flux-LoRA"
trigger_word = "3D Portrait"  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

💻 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 = "prithivMLmods/Castor-3D-Portrait-Flux-LoRA"
trigger_word = "3D Portrait"  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

# Generate an image
prompt = f"{trigger_word}, A 3D Portrait cartoon depiction of a woman with long dark brown hair and brown eyes stands in front of a window."
image = pipe(prompt).images[0]
image.show()

📚 Documentation

Model Description

prithivMLmods/Castor-3D-Portrait-Flux-LoRA

Property	Details
Base Model	black-forest-labs/FLUX.1-dev
Instance Prompt	3D Portrait
Model Type	LoRA for text-to-image
LR Scheduler	constant
Optimizer	AdamW
Network Dim	64
Network Alpha	32
Epoch	15
Noise Offset	0.03
Multires Noise Discount	0.1
Multires Noise Iterations	10
Repeat & Steps	20 & 2.5K
Save Every N Epochs	1
Labeling	florence2-en(natural language & English)
Total Images Used for Training	19

App File Structure

/project-root/ ├── .gitattributes
├── README.md
├── app.py
├── pythonproject.py

📄 License

This model is licensed under creativeml-openrail-m.

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