The dreambooth_diffusion_toy open-source model - Generate toy images in a specific style for free!

Dreambooth Diffusion Toy

Developed by keras-dreambooth

This is a stable diffusion model fine-tuned with DreamBooth, specifically designed for generating toy images in specific styles.

Image Generation Open Source License:Openrail #Custom Rabbit Toy Generation #Keras Fine-tuned Diffusion Model #Creative Toy Image Generation

Downloads 31

Release Time : 3/18/2023

Model Overview

This model was fine-tuned by ChienVM on a specific toy dataset, capable of generating high-quality toy images based on text prompts, supporting various styles and scenes.

Model Features

Specific Concept Learning

The model has learned the specific toy concept 'hks## toy' and can accurately generate images of this toy.

Multi-style Support

Supports generating toy images in different artistic styles (e.g., Van Gogh style) and scenes (e.g., beach, Christmas).

High-Quality Generation

Capable of generating high-quality images at 512x512 resolution with rich details.

Model Capabilities

Text-to-Image Generation

Style Transfer

Scene Composition

Use Cases

Creative Design

Holiday Theme Design

Generate images of toys dressed in Santa Claus outfits

Can be used for holiday cards or decoration designs

Artistic Creation

Generate Van Gogh-style toy oil paintings

Can be used for artistic inspiration or digital artwork

Marketing

Product Showcase

Generate toy photos in different scenes

Can be used for product brochures or website displays

🚀 tf-keras

This is a model fine - tuned to learn the concept of Mother rabbit toy, suitable for text - to - image generation tasks.

🚀 Quick Start

This model has been fine - tuned to learn the concept of Mother rabbit toy. You can use it for text - to - image generation by providing prompts related to the concept token "hks## toy".

✨ Features

Fine - tuned to learn the concept of Mother rabbit toy.
Can generate various images based on different prompts related to "hks## toy".

📚 Documentation

🔍 Model description

This model has been fine - tuned to learn the concept of Mother rabbit toy by ChienVM on this dataset

📋 Intended uses & limitations

Concept token "hks## toy". Example: "a photo of hks## toy "

🖼️ Some examples prompt

Sample 1 — Prompt: a photo of hks## toy in Santa Claus clothes. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

Sample 2 — Prompt: a oil painting of hks## toy in style of van gogh. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

Sample 3 — Prompt: a photo of hks## toy standing on the beach at sunset. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

⚙️ Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Property	Details
inner_optimizer.class_name	Custom>RMSprop
inner_optimizer.config.name	RMSprop
inner_optimizer.config.weight_decay	None
inner_optimizer.config.clipnorm	None
inner_optimizer.config.global_clipnorm	None
inner_optimizer.config.clipvalue	None
inner_optimizer.config.use_ema	False
inner_optimizer.config.ema_momentum	0.99
inner_optimizer.config.ema_overwrite_frequency	100
inner_optimizer.config.jit_compile	True
inner_optimizer.config.is_legacy_optimizer	False
inner_optimizer.config.learning_rate	0.0010000000474974513
inner_optimizer.config.rho	0.9
inner_optimizer.config.momentum	0.0
inner_optimizer.config.epsilon	1e - 07
inner_optimizer.config.centered	False
dynamic	True
initial_scale	32768.0
dynamic_growth_steps	2000
training_precision	mixed_float16

📄 License

This model is under the creativeml - openrail - m 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