Hugging Face's logo

tensorart
/
Bokeh_Line_Controlnet

Text-to-Image
Diffusers
Safetensors
English
Model card Files Community
Bokeh_Line_Controlnet / README.md
coco22's picture
coco22
Update README.md
fc46238 verified
preview code
|
raw
history blame contribute delete
2.25 kB
metadata
license: other
license_name: stabilityai-ai-community
license_link: LICENSE.md
language:
  - en
base_model:
  - tensorart/bokeh_3.5_medium
pipeline_tag: text-to-image

Bokeh_Line_Controlnet

Description

  • Input Image: Black and white line art or images processed with edge detection algorithms
  • Output Image: Generated images incorporating edge information

This enables better control over the main subject features and composition, resulting in more vivid and realistic images.

Example

input output Prompt
A cat looks up, close-up, sapphire eyes
heron bird standing, closeup, graceful
a modern build design
A old woman talking

Use

We recommend using ComfyUI for local inference input

With Bokeh 

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_Line_Controlnet/resolve/main/images/001_line.png")
prompt = "A cat looks up, close-up, sapphire eyes"
negative_prompt ="anime,render,cartoon,3d"
negative_prompt_3=""

image = pipe(
    prompt, 
    num_inference_steps=30,
    negative_prompt=negative_prompt,
    negative_prompt_3=negative_prompt_3,
    control_image=control_image, 
    height=1728,
    width=1152,
    guidance_scale=4,
    controlnet_conditioning_scale=0.8
).images[0]
image.save('image.jpg')

Contact