Real-Claymation Open-Source Text-to-Image Model - Freely Generate Images with Realistic Claymation Effects

Real Claymation

Developed by strangerzonehf

A text-to-image generation model based on LoRA and diffusion models, specifically designed for generating realistic claymation-style images.

Image Generation Open Source License:Apache-2.0 #Clay-style generation #Low-angle close-up #LoRA fine-tuning

Downloads 37

Release Time : 2/27/2025

Model Overview

This model can generate images with realistic claymation style based on text descriptions, suitable for creative design, animation production, and other fields.

Model Features

Realistic Claymation Style

Capable of generating images with realistic claymation texture, including various themes such as characters and animals.

LoRA Fine-tuning

Fine-tunes the base diffusion model using LoRA technology to achieve specific style image generation.

Multi-angle Support

Supports image generation from various shooting angles like low-angle shots and close-ups.

Model Capabilities

Text-to-image generation

Specific style image generation

Multi-angle image generation

Use Cases

Creative Design

Claymation Character Design

Generates various claymation-style character images based on text descriptions

Can generate claymation characters with specific features (e.g., hats, scarves, etc.)

Scene Design

Generates claymation-style scene images

Can generate complete claymation scenes with backgrounds

Animation Production

Animation Material Generation

Provides materials for claymation production

Can generate individual characters or scenes usable for animation production

🚀 Real-Claymation

This is a text - to - image model based on LoRA and Diffusers, capable of generating real - claymation style images.

🚀 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 = "strangerzonehf/Real-Claymation"
trigger_word = "333 Pro Sketch"  
pipe.load_lora_weights(lora_repo)

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

Image Generation

You should use Real Claymation to trigger the image generation.

✨ Features

Model Details:
- Base Model: black - forest - labs/FLUX.1 - dev
- Instance Prompt: Real Claymation
- License: apache - 2.0
Visual Examples:
- Multiple examples of generated images are provided with corresponding text prompts. You can view them in the widget section below.

📦 Installation

The installation steps are shown in the "Setting Up" section. You need to import relevant libraries, load the base model and LoRA weights, and set up the device.

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/Real-Claymation"
trigger_word = "333 Pro Sketch"  
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 = "strangerzonehf/Real-Claymation"
trigger_word = "333 Pro Sketch"  
pipe.load_lora_weights(lora_repo)

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

# Use the trigger word to generate an image
prompt = "Real Claymation"
image = pipe(prompt).images[0]
image.show()

📚 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	25 & 3100
Epoch	21	Save Every N Epochs	1

Labeling: florence2 - en(natural language & English)

Total Images Used for Training : 28

Best Dimensions & Inference

Dimensions	Aspect Ratio	Recommendation
1280 x 832	3:2	Best
1024 x 1024	1:1	Default

Inference Range

Recommended Inference Steps: 30–35

Trigger words

You should use Real Claymation to trigger the image generation.

Download model

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

📄 License

This model is licensed under the apache - 2.0 license.

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