Spaces:
Paused
Paused
File size: 3,862 Bytes
7db9ab2 39544af 7db9ab2 39544af 7db9ab2 39544af 8ca38ac 39544af 7db9ab2 39544af 7db9ab2 39544af 7db9ab2 39544af 7db9ab2 39544af 7db9ab2 39544af 7db9ab2 f93e041 7db9ab2 39544af 7db9ab2 39544af 7db9ab2 |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
import gradio
import torch
import numpy
from PIL import Image
from torchvision import transforms
#from torchvision import transforms
from diffusers import StableDiffusionInpaintPipeline
#from diffusers import StableDiffusionUpscalePipeline
#from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
from diffusers import DPMSolverMultistepScheduler
deviceStr = "cuda" if torch.cuda.is_available() else "cpu"
device = torch.device(deviceStr)
if deviceStr == "cuda":
pipeline = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting",
revision="fp16",
torch_dtype=torch.float16,
safety_checker=lambda images, **kwargs: (images, False))
pipeline.to(device)
pipeline.enable_xformers_memory_efficient_attention()
else:
pipeline = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting",
safety_checker=lambda images, **kwargs: (images, False))
#superresolutionPipe = StableDiffusionUpscalePipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler")
#pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
#generator = torch.Generator(device).manual_seed(seed)
latents = torch.randn((1, 4, 64, 64), device=device)
schedulers = [
"DDIMScheduler", "LMSDiscreteScheduler", "PNDMScheduler"
]
latentNoiseInputs = [
"Uniform", "Low Discrepency Sequence"
]
imageSize = (512, 512, 3)
imageSize2 = (512, 512)
#lastImage = Image.new(mode="RGB", size=(imageSize[0], imageSize[1]))
def diffuse(prompt, negativePrompt, inputImage, mask, guidanceScale, numInferenceSteps, seed, noiseScheduler, latentNoise):
#width = inputImage.size[1]
#height = 512
#print(inputImage.size)
#image = numpy.resize(inputImage, imageSize)
#pilImage.thumbnail(imageSize2)
#transforms.Resize(imageSize2)(inputImage)
#pilImage = Image.fromarray(inputImage)
#pilImage.resize(imageSize2)
#imageArray = numpy.asarray(pilImage)
#inputImage = torch.nn.functional.interpolate(inputImage, size=imageSize)
if mask is None:
return inputImage
generator = torch.Generator(device).manual_seed(seed)
newImage = pipeline(prompt=prompt,
negative_prompt=negativePrompt,
image=inputImage,
mask_image=mask,
guidance_scale=guidanceScale,
num_inference_steps=numInferenceSteps,
generator=generator).images[0]
return newImage
prompt = gradio.Textbox(label="Prompt", placeholder="A person in a room", lines=3)
negativePrompt = gradio.Textbox(label="Negative Prompt", placeholder="Text", lines=3)
#inputImage = gradio.Image(label="Input Image", type="pil")
inputImage = gradio.Image(label="Input Feed", source="webcam", shape=[512,512], streaming=True)
mask = gradio.Image(label="Mask", type="pil")
outputImage = gradio.Image(label="Extrapolated Field of View")
guidanceScale = gradio.Slider(label="Guidance Scale", maximum=1, value=0.75)
numInferenceSteps = gradio.Slider(label="Number of Inference Steps", maximum=100, value=25)
seed = gradio.Slider(label="Generator Seed", maximum=1000, value=512)
noiseScheduler = gradio.Dropdown(schedulers, label="Noise Scheduler", value="DDIMScheduler")
latentNoise = gradio.Dropdown(latentNoiseInputs, label="Latent Noise", value="Iniform")
inputs=[prompt, negativePrompt, inputImage, mask, guidanceScale, numInferenceSteps, seed, noiseScheduler, latentNoise]
ux = gradio.Interface(fn=diffuse, title="View Diffusion", inputs=inputs, outputs=outputImage, live=True)
ux.launch() |