Spaces:
Runtime error
Runtime error
File size: 2,922 Bytes
95e4531 |
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 |
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from utils import write_video, dummy
from PIL import Image
import numpy as np
import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"
import torch
import gradio as gr
def stable_diffusion_zoom_out(
repo_id="stabilityai/stable-diffusion-2-inpainting",
original_prompt="a dog",
negative_prompt="a cat",
steps=32,
num_frames=10,
):
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, revision="fp16")
pipe.set_use_memory_efficient_attention_xformers(True)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
pipe.safety_checker = dummy
current_image = Image.new(mode="RGBA", size=(512, 512))
mask_image = np.array(current_image)[:,:,3] # assume image has alpha mask (use .mode to check for "RGBA")
mask_image = Image.fromarray(255-mask_image).convert("RGB")
current_image = current_image.convert("RGB")
num_images = 1
prompt = [original_prompt] * num_images
negative_prompt = [negative_prompt] * num_images
images = pipe(prompt=prompt, negative_prompt=negative_prompt, image=current_image, mask_image=mask_image, num_inference_steps=25)[0]
current_image = images[0]
all_frames = []
all_frames.append(current_image)
for i in range(num_frames):
next_image = np.array(current_image.convert("RGBA"))*0
prev_image = current_image.resize((512-2*steps,512-2*steps))
prev_image = prev_image.convert("RGBA")
prev_image = np.array(prev_image)
next_image[:, :, 3] = 1
next_image[steps:512-steps,steps:512-steps,:] = prev_image
prev_image = Image.fromarray(next_image)
current_image = prev_image
mask_image = np.array(current_image)[:,:,3] # assume image has alpha mask (use .mode to check for "RGBA")
mask_image = Image.fromarray(255-mask_image).convert("RGB")
current_image = current_image.convert("RGB")
images = pipe(prompt=prompt, negative_prompt=negative_prompt, image=current_image, mask_image=mask_image, num_inference_steps=25)[0]
current_image = images[0]
current_image.paste(prev_image, mask=prev_image)
all_frames.append(current_image)
save_path = "infinite_zoom_out.mp4"
write_video(save_path, all_frames, fps=16)
return save_path
inputs = [
gr.Dropdown(["stabilityai/stable-diffusion-2-inpainting"], label="Model"),
gr.inputs.Textbox(lines=1, default="a dog", label="Prompt"),
gr.inputs.Textbox(lines=1, default="a cat", label="Negative Prompt"),
gr.inputs.Slider(minimum=1, maximum=64, default=32, label="Steps"),
gr.inputs.Slider(minimum=1, maximum=100, default=10, label="Frames"),
]
output = gr.outputs.Video()
title = "Stable Diffusion Infinite Zoom Out"
demo_app = gr.Interface(
fn=stable_diffusion_zoom_out,
inputs=inputs,
outputs=output,
title=title,
theme='huggingface',
)
demo_app.launch(debug=True, enable_queue=True)
|