BRIA-3.2-ControlNet-Generative-Fill, Model Card
BRIA 3.2 ControlNet-Generative-Fill, trained on the foundation of BRIA 3.2 Text-to-Image, enables the generation of high-quality images guided by a textual prompt and a mask. This allows for immersive addition and modification of objects in a given input image.
Model Description
Developed by: BRIA AI
Model type: ControlNet for Latent diffusion
License: bria-3.2
Model Description: ControlNet Generative-Fill for BRIA 3.2 Text-to-Image model. The model inpaints objects guided by a textual prompt and a mask.
Resources for more information: BRIA AI
Usage
Installation
pip install -qr https://huggingface.co/briaai/bria-3.2-controlnet-generative-fill/resolve/main/requirements.txt
install the latest version of diffusers:
pip install git+https://github.com/huggingface/diffusers
from huggingface_hub import hf_hub_download
import os
try:
local_dir = os.path.dirname(__file__)
except:
local_dir = '.'
hf_hub_download(repo_id="briaai/BRIA-3.2-ControlNet-Generative-Fill", filename='controlnet_bria.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-3.2-ControlNet-Generative-Fill", filename='pipeline_bria_controlnet_inpainting.py', local_dir=local_dir)
Run Inpainting script
from io import BytesIO
import requests
import torch
from PIL import Image
from PIL.Image import Image as ImageType
from controlnet_bria import BriaControlNetModel
from pipeline_bria_controlnet_inpainting import BriaControlNetInpaintingPipeline
GRANULARITY_VAL = 8
def load_gpu_pipeline_from_models():
transformer_path = "briaai/BRIA-3.2"
print("Done getting transformer")
print("Getting ControlNet")
controlnet = BriaControlNetModel.from_pretrained("briaai/BRIA-3.2-ControlNet-Generative-Fill")
print("Done getting controlnet")
transformer_path = "briaai/BRIA-3.2"
pipeline = BriaControlNetInpaintingPipeline.from_pretrained(transformer_path,
revision="pre_diffusers_support" ,
controlnet=controlnet, torch_dtype=torch.bfloat16,
trust_remote_code=True)
pipeline = pipeline.to(device="cuda", dtype=torch.bfloat16)
pipeline.enable_model_cpu_offload()
return pipeline
def download_image(url):
response = requests.get(url)
return Image.open(BytesIO(response.content))
def resize_image_to_retain_ratio(image):
pixel_number = 1024*1024
ratio = image.size[0] / image.size[1]
width = int((pixel_number * ratio) ** 0.5)
width = width - (width % GRANULARITY_VAL)
height = int(pixel_number / width)
height = height - (height % GRANULARITY_VAL)
image = image.resize((width, height))
return image
def infer(pipeline: BriaControlNetInpaintingPipeline,
input_image: ImageType,
mask_image: ImageType,
prompt: str,
negative_prompt: str,
num_inference_steps: int,
seed: int,
guidance_scale: float,
controlnet_conditioning_scale: float,
):
generator = torch.Generator(device="cuda").manual_seed(seed)
with torch.no_grad():
res_image = self.pipeline(
prompt=prompt,
control_image=[image],
num_inference_steps=num_inference_steps,
generator=generator,
guidance_scale=guidance_scale,
height=image.size[1],
width=image.size[0],
negative_prompt=negative_prompt,
max_sequence_length=128,
control_mode=None,
controlnet_conditioning_scale=self.eval_args.controlnet_conditioning_scale,
mask=mask,
).images[0]
return image_arr
gpu_pipeline = load_gpu_pipeline_from_models()
seed = 9871256
# call parameters we set for optimal results
num_inference_steps = 50
guidance_scale = 5.0
controlnet_conditioning_scale = 1.0
- Downloads last month
- -