Flux-Master-Claymation Open-source Image Generation Model - Free to Generate Claymation-style Plastic Doll/Animal Images

Flux Master Claymation

Developed by strangerzonehf

A LoRA-based text-to-image diffusion model specialized in generating clay animation-style plastic figurines/animals

Text-to-Image Open Source License:Apache-2.0 #Claymation Style Generation #LoRA Fine-tuned Diffusion Model #Stop-Motion Texture

Downloads 85

Release Time : 4/12/2025

Model Overview

This model employs LoRA fine-tuning to stylize the base diffusion model, capable of generating vivid 3D-rendered clay-style images with stop-motion textures based on text descriptions. Particularly excels in showcasing plastic material gloss, miniature scene lighting, and dramatic compositions.

Model Features

Claymation Stylization

Fine-tuned with 45 professional clay animation materials, accurately recreating plastic textures and stop-motion lighting effects

Efficient LoRA Adaptation

Utilizes lightweight adaptation structure with network dimension 64/Alpha 32, achieving style transfer while preserving base model capabilities

Multi-Resolution Support

Supports 1280x832 (3:2) and 1024x1024 (1:1) recommended resolutions, optimized with multi-resolution noise attenuation technology

Model Capabilities

Text-Guided Image Generation

Clay Material Rendering

Miniature Scene Construction

Dramatic Lighting Control

Use Cases

Digital Art Creation

Stop-Motion Concept Design

Rapidly generate clay animation character prototypes and scene concepts

Complete compositions like the desert expedition team and café scenes in examples

Educational Demonstration

Animation Teaching Materials

Generate typical pose sequences for animation principle instruction

Dynamic moments like the golden retriever's tail wagging in examples

🚀 Flux-Master-Claymation

This project is a text - to - image model based on LoRA and Diffusers, which can generate high - quality claymation - style images.

🚀 Quick Start

Setting Up

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-Master-Claymation"
trigger_word = "Master Claymation"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use Master Claymation to trigger the image generation.

✨ Features

Text - to - Image Generation: Generate claymation - style images based on text prompts.
Model Customization: Built on LoRA technology, allowing for fine - tuning and customization.

📦 Installation

The code example in the "Setting Up" section shows the basic steps to load the model. You need to have the necessary Python libraries installed, such as torch and pipelines.

💻 Usage Examples

Basic Usage

The following code demonstrates how to set up the model and use the trigger word to generate images:

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-Master-Claymation"
trigger_word = "Master Claymation"  
pipe.load_lora_weights(lora_repo)

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

📚 Documentation

Model description for Flux - Master - Claymation

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	28 & 3450
Epoch	27	Save Every N Epochs	1

Labeling: florence2 - en(natural language & English)

Total Images Used for Training : 45

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

📄 License

This model is licensed under the apache - 2.0 license.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

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