File size: 3,031 Bytes
7efaeeb 4c67855 3451c21 c11e306 4c67855 c11e306 4c67855 3451c21 c11e306 7efaeeb 4c67855 7efaeeb 0538750 4c67855 21d4e0f 3451c21 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import torch
from PIL import Image
from diffusers import ControlNetModel, DiffusionPipeline
from diffusers.utils import load_image
import gradio as gr
import warnings
warnings.filterwarnings("ignore")
def resize_for_condition_image(input_image: Image, resolution: int):
input_image = input_image.convert("RGB")
W, H = input_image.size
k = float(resolution) / min(H, W)
H *= k
W *= k
H = int(round(H / 64.0)) * 64
W = int(round(W / 64.0)) * 64
img = input_image.resize((W, H), resample=Image.LANCZOS)
return img
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
controlnet = ControlNetModel.from_pretrained('lllyasviel/control_v11f1e_sd15_tile',
torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",
custom_pipeline="stable_diffusion_controlnet_img2img",
controlnet=controlnet,
torch_dtype=torch.float16).to(device)
pipe.enable_xformers_memory_efficient_attention()
def super_esr(source_image,prompt,negative_prompt,strength,seed,num_inference_steps):
condition_image = resize_for_condition_image(source_image, 1024)
generator = torch.Generator(device="cuda").manual_seed(seed)
image = pipe(prompt=prompt,#"best quality",
negative_prompt="blur, lowres, bad anatomy, bad hands, cropped, worst quality",
image=condition_image,
controlnet_conditioning_image=condition_image,
width=condition_image.size[0],
height=condition_image.size[1],
strength=1.0,
generator=generator,
num_inference_steps=num_inference_steps,
).images[0]
# print(source_image,prompt,negative_prompt,strength,seed,num_inference_steps)
return image
# define and take input the same as the super_esr function
inputs=[
gr.inputs.Image(type="pil",label="Source Image"),
gr.inputs.Textbox(lines=2,label="Prompt"),
gr.inputs.Textbox(lines=2,label="Negative Prompt"),
gr.inputs.Slider(minimum=0,maximum=1,label="Strength"),
gr.inputs.Slider(minimum=0,maximum=100,label="Seed"),
gr.inputs.Slider(minimum=0,maximum=100,label="Num Inference Steps")
]
outputs=[
gr.outputs.Image(type="pil",label="Output Image")
]
title="Super ESR"
description="Super ESR is a super resolution model that uses diffusion to generate high resolution images from low resolution images"
examples=[
["https://i.imgur.com/9IqyX1F.png","best quality","blur, lowres, bad anatomy, bad hands, cropped, worst quality",1.0,0,100],
["https://i.imgur.com/9IqyX1F.png","best quality","blur, lowres, bad anatomy, bad hands, cropped, worst quality",1.0,0,100],
]
# create a queue of the requests
x=gr.Interface(fn=super_esr,inputs=inputs,outputs=outputs,title=title,description=description,examples=examples)
x.launch()
|