Bokeh_Depth_Controlnet Open-source Image Generation Model - Control Depth of Field and Spatial Structure with Depth Maps

Bokeh Depth Controlnet

Developed by tensorart

An image generation model based on depth information that can control the depth of field effect and spatial structure of generated images through depth maps.

Image Generation EnglishOpen Source License:Other #Depth Map Control #Depth of Field Enhancement #Spatial Structure Generation

Downloads 109

Release Time : 4/7/2025

Model Overview

This model integrates depth information maps generated by depth estimation models, enabling the base model to better understand spatial relationships within images and achieve more precise depth of field control and 3D effect generation.

Model Features

Depth Information Integration

Through depth map input, the model can more accurately understand the spatial structure of images and generate images with realistic depth of field effects.

Precise Depth of Field Control

Can precisely control the focus and blur areas of generated images based on depth information, creating professional-grade photographic effects.

3D Spatial Perception

The model has the ability to understand three-dimensional spatial relationships and can generate more three-dimensional images.

Model Capabilities

Text-to-Image

Depth of Field Control

Spatial Structure Generation

Image Enhancement

Use Cases

Photography Effect Enhancement

Portrait Photography

Add professional-grade depth of field effects to portrait photos, highlighting the subject while blurring the background

Generate portrait works with professional photographic quality

Product Showcase

Add artistic focus effects to product images to enhance visual appeal

Create product display images with commercial quality

Creative Art

Sci-Fi Scene Creation

Generate sci-fi scenes with depth, such as space, futuristic cities, etc.

Create sci-fi artworks with a sense of three-dimensionality and spatial depth

Natural Scene Rendering

Add realistic depth of field effects to natural landscapes to enhance the sense of layering in the image

Generate natural scene images with photographic realism

🚀 Bokeh_Depth_Controlnet

Bokeh_Depth_Controlnet is a text - to - image model that uses depth information to generate more realistic depth - of - field effects and control spatial structures.

🚀 Quick Start

We recommend using ComfyUI for local inference. input

✨ Features

Input Image: Depth information map generated by depth estimation model.
Output Image: The base model integrates depth information for control, generating more realistic depth - of - field effects and spatial structure control.

The depth map enables the model to better understand spatial relationships within images, achieving more precise depth - of - field control and three - dimensional effect generation.

💻 Usage Examples

Basic Usage

import torch
from diffusers import StableDiffusion3ControlNetPipeline
from diffusers import SD3ControlNetModel
from diffusers.utils import load_image

controlnet = SD3ControlNetModel.from_pretrained("tensorart/Bokeh_Depth_Controlnet")
pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
    "tensorart/bokeh_3.5_medium",
    controlnet=controlnet
)
pipe.to("cuda", torch.float16)

control_image = load_image("https://huggingface.co/tensorart/Bokeh_Depth_Controlnet/resolve/main/images/001_depth.png")
prompt = "A old man talking"
negative_prompt ="anime,render,cartoon,3d,bad hands,extra finger"
negative_prompt_3=""

image = pipe(
    prompt, 
    num_inference_steps=28,
    negative_prompt=negative_prompt, 
    negative_prompt_3=negative_prompt_3,
    control_image=control_image, 
    height=1440,
    width=1440,
    guidance_scale=4,
    controlnet_conditioning_scale=0.85
).images[0]
image.save('image.jpg')

📚 Documentation

input	output	Prompt
		a old man
		A lone astronaut in a white suit and helmet, with a backpack, strolls on a rocky, red landscape under a star galaxy
		a eagle , black background
		A crystal heart sits on a gnarly, moss - covered log, with a galaxy background

📄 License

License: other
License Name: stabilityai - ai - community
License Link: LICENSE.md

📞 Contact

Website: https://tensor.art https://tusiart.com
Developed by: TensorArt
Api: https://tams.tensor.art/

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