GeorgLegato
GitHub
commit
8da6fb3a44
|
|
@ -1,2 +1,2 @@
|
|||
from .image import shrink_and_paste_on_blank
|
||||
from .video import write_video
|
||||
from .ui import on_ui_tabs
|
||||
from .settings import on_ui_settings
|
||||
|
|
|
|||
|
|
@ -0,0 +1,125 @@
|
|||
import math
|
||||
import os
|
||||
import json
|
||||
from jsonschema import validate
|
||||
import modules.shared as shared
|
||||
import modules.sd_models
|
||||
import gradio as gr
|
||||
from scripts import postprocessing_upscale
|
||||
from .static_variables import jsonprompt_schemafile
|
||||
|
||||
|
||||
def fix_env_Path_ffprobe():
|
||||
envpath = os.environ["PATH"]
|
||||
ffppath = shared.opts.data.get("infzoom_ffprobepath", "")
|
||||
|
||||
if ffppath and not ffppath in envpath:
|
||||
path_sep = ";" if os.name == "nt" else ":"
|
||||
os.environ["PATH"] = envpath + path_sep + ffppath
|
||||
|
||||
|
||||
def closest_upper_divisible_by_eight(num):
|
||||
if num % 8 == 0:
|
||||
return num
|
||||
else:
|
||||
return math.ceil(num / 8) * 8
|
||||
|
||||
|
||||
def load_model_from_setting(model_field_name, progress, progress_desc):
|
||||
# fix typo in Automatic1111 vs Vlad111
|
||||
if hasattr(modules.sd_models, "checkpoint_alisases"):
|
||||
checkPList = modules.sd_models.checkpoint_alisases
|
||||
elif hasattr(modules.sd_models, "checkpoint_aliases"):
|
||||
checkPList = modules.sd_models.checkpoint_aliases
|
||||
else:
|
||||
raise Exception(
|
||||
"This is not a compatible StableDiffusion Platform, can not access checkpoints"
|
||||
)
|
||||
|
||||
model_name = shared.opts.data.get(model_field_name)
|
||||
if model_name is not None and model_name != "":
|
||||
checkinfo = checkPList[model_name]
|
||||
|
||||
if not checkinfo:
|
||||
raise NameError(model_field_name + " Does not exist in your models.")
|
||||
|
||||
if progress:
|
||||
progress(0, desc=progress_desc + checkinfo.name)
|
||||
|
||||
modules.sd_models.load_model(checkinfo)
|
||||
|
||||
|
||||
def do_upscaleImg(curImg, upscale_do, upscaler_name, upscale_by):
|
||||
if not upscale_do:
|
||||
return curImg
|
||||
|
||||
# ensure even width and even height for ffmpeg
|
||||
# if odd, switch to scale to mode
|
||||
rwidth = round(curImg.width * upscale_by)
|
||||
rheight = round(curImg.height * upscale_by)
|
||||
|
||||
ups_mode = 2 # upscale_by
|
||||
if (rwidth % 2) == 1:
|
||||
ups_mode = 1
|
||||
rwidth += 1
|
||||
if (rheight % 2) == 1:
|
||||
ups_mode = 1
|
||||
rheight += 1
|
||||
|
||||
if 1 == ups_mode:
|
||||
print(
|
||||
"Infinite Zoom: aligning output size to even width and height: "
|
||||
+ str(rwidth)
|
||||
+ " x "
|
||||
+ str(rheight),
|
||||
end="\r",
|
||||
)
|
||||
|
||||
pp = postprocessing_upscale.scripts_postprocessing.PostprocessedImage(curImg)
|
||||
ups = postprocessing_upscale.ScriptPostprocessingUpscale()
|
||||
ups.process(
|
||||
pp,
|
||||
upscale_mode=ups_mode,
|
||||
upscale_by=upscale_by,
|
||||
upscale_to_width=rwidth,
|
||||
upscale_to_height=rheight,
|
||||
upscale_crop=False,
|
||||
upscaler_1_name=upscaler_name,
|
||||
upscaler_2_name=None,
|
||||
upscaler_2_visibility=0.0,
|
||||
)
|
||||
return pp.image
|
||||
|
||||
|
||||
def validatePromptJson_throws(data):
|
||||
with open(jsonprompt_schemafile, "r") as s:
|
||||
schema = json.load(s)
|
||||
validate(instance=data, schema=schema)
|
||||
|
||||
|
||||
def putPrompts(files):
|
||||
try:
|
||||
with open(files.name, "r") as f:
|
||||
file_contents = f.read()
|
||||
data = json.loads(file_contents)
|
||||
validatePromptJson_throws(data)
|
||||
return [
|
||||
gr.DataFrame.update(data["prompts"]),
|
||||
gr.Textbox.update(data["negPrompt"]),
|
||||
]
|
||||
|
||||
except Exception:
|
||||
gr.Error(
|
||||
"loading your prompt failed. It seems to be invalid. Your prompt table is preserved."
|
||||
)
|
||||
print(
|
||||
"[InfiniteZoom:] Loading your prompt failed. It seems to be invalid. Your prompt table is preserved."
|
||||
)
|
||||
return [gr.DataFrame.update(), gr.Textbox.update()]
|
||||
|
||||
|
||||
def clearPrompts():
|
||||
return [
|
||||
gr.DataFrame.update(value=[[0, "Infinite Zoom. Start over"]]),
|
||||
gr.Textbox.update(""),
|
||||
]
|
||||
|
|
@ -4,8 +4,9 @@ import matplotlib.pyplot as plt
|
|||
|
||||
# Define the values for width, mask_width, and num_interpol_frames
|
||||
width = 512
|
||||
mask_width = round(width*0.49)
|
||||
num_interpol_frames = 90
|
||||
|
||||
mask_width = round(width*0.25)
|
||||
num_interpol_frames = 30
|
||||
|
||||
# Create a list to store the values of interpol_width for each frame
|
||||
interpol_width_values = []
|
||||
|
|
|
|||
|
|
@ -21,6 +21,9 @@
|
|||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
}
|
||||
|
|
@ -36,7 +39,7 @@
|
|||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"minItems": 2
|
||||
"minItems": 3
|
||||
}
|
||||
},
|
||||
"required": ["data", "headers"]
|
||||
|
|
@ -0,0 +1,436 @@
|
|||
import math, time, os
|
||||
import numpy as np
|
||||
from PIL import Image, ImageDraw, ImageFilter, ImageOps
|
||||
from modules.ui import plaintext_to_html
|
||||
import modules.shared as shared
|
||||
|
||||
from .helpers import (
|
||||
fix_env_Path_ffprobe,
|
||||
closest_upper_divisible_by_eight,
|
||||
load_model_from_setting,
|
||||
do_upscaleImg,
|
||||
)
|
||||
from .sd_helpers import renderImg2Img, renderTxt2Img
|
||||
from .image import shrink_and_paste_on_blank
|
||||
from .video import write_video
|
||||
|
||||
|
||||
def create_zoom(
|
||||
prompts_array,
|
||||
negative_prompt,
|
||||
num_outpainting_steps,
|
||||
guidance_scale,
|
||||
num_inference_steps,
|
||||
custom_init_image,
|
||||
custom_exit_image,
|
||||
video_frame_rate,
|
||||
video_zoom_mode,
|
||||
video_start_frame_dupe_amount,
|
||||
video_last_frame_dupe_amount,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
zoom_speed,
|
||||
seed,
|
||||
outputsizeW,
|
||||
outputsizeH,
|
||||
batchcount,
|
||||
sampler,
|
||||
upscale_do,
|
||||
upscaler_name,
|
||||
upscalerinterpol_name,
|
||||
upscale_by,
|
||||
exitgamma,
|
||||
maskwidth_slider,
|
||||
maskheight_slider,
|
||||
progress=None,
|
||||
):
|
||||
|
||||
for i in range(batchcount):
|
||||
print(f"Batch {i+1}/{batchcount}")
|
||||
result = create_zoom_single(
|
||||
prompts_array,
|
||||
negative_prompt,
|
||||
num_outpainting_steps,
|
||||
guidance_scale,
|
||||
num_inference_steps,
|
||||
custom_init_image,
|
||||
custom_exit_image,
|
||||
video_frame_rate,
|
||||
video_zoom_mode,
|
||||
video_start_frame_dupe_amount,
|
||||
video_last_frame_dupe_amount,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
zoom_speed,
|
||||
seed,
|
||||
outputsizeW,
|
||||
outputsizeH,
|
||||
sampler,
|
||||
upscale_do,
|
||||
upscaler_name,
|
||||
upscalerinterpol_name,
|
||||
upscale_by,
|
||||
exitgamma,
|
||||
maskwidth_slider,
|
||||
maskheight_slider,
|
||||
progress
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def create_zoom_single(
|
||||
prompts_array,
|
||||
negative_prompt,
|
||||
num_outpainting_steps,
|
||||
guidance_scale,
|
||||
num_inference_steps,
|
||||
custom_init_image,
|
||||
custom_exit_image,
|
||||
video_frame_rate,
|
||||
video_zoom_mode,
|
||||
video_start_frame_dupe_amount,
|
||||
video_last_frame_dupe_amount,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
zoom_speed,
|
||||
seed,
|
||||
outputsizeW,
|
||||
outputsizeH,
|
||||
sampler,
|
||||
upscale_do,
|
||||
upscaler_name,
|
||||
upscalerinterpol_name,
|
||||
upscale_by,
|
||||
exitgamma,
|
||||
maskwidth_slider,
|
||||
maskheight_slider,
|
||||
progress=None,
|
||||
):
|
||||
# try:
|
||||
# if gr.Progress() is not None:
|
||||
# progress = gr.Progress()
|
||||
# progress(0, desc="Preparing Initial Image")
|
||||
# except Exception:
|
||||
# pass
|
||||
fix_env_Path_ffprobe()
|
||||
|
||||
prompts = {}
|
||||
prompt_images = {}
|
||||
|
||||
for x in prompts_array:
|
||||
try:
|
||||
key = int(x[0])
|
||||
value = str(x[1])
|
||||
file_loc = str(x[2])
|
||||
prompts[key] = value
|
||||
prompt_images[key] = file_loc
|
||||
except ValueError:
|
||||
pass
|
||||
assert len(prompts_array) > 0, "prompts is empty"
|
||||
print(str(len(prompts)) + " prompts found")
|
||||
print(str(len(prompt_images)) + " prompts Images found")
|
||||
|
||||
width = closest_upper_divisible_by_eight(outputsizeW)
|
||||
height = closest_upper_divisible_by_eight(outputsizeH)
|
||||
|
||||
current_image = Image.new(mode="RGBA", size=(width, height))
|
||||
mask_image = np.array(current_image)[:, :, 3]
|
||||
mask_image = Image.fromarray(255 - mask_image).convert("RGB")
|
||||
current_image = current_image.convert("RGB")
|
||||
current_seed = seed
|
||||
extra_frames = 0
|
||||
|
||||
if custom_init_image:
|
||||
current_image = custom_init_image.resize(
|
||||
(width, height), resample=Image.LANCZOS
|
||||
)
|
||||
print("using Custom Initial Image")
|
||||
else:
|
||||
if prompt_images[min(k for k in prompt_images.keys() if k >= 0)] == "":
|
||||
load_model_from_setting(
|
||||
"infzoom_txt2img_model", progress, "Loading Model for txt2img: "
|
||||
)
|
||||
|
||||
processed, current_seed = renderTxt2Img(
|
||||
prompts[min(k for k in prompts.keys() if k >= 0)],
|
||||
negative_prompt,
|
||||
sampler,
|
||||
num_inference_steps,
|
||||
guidance_scale,
|
||||
current_seed,
|
||||
width,
|
||||
height,
|
||||
)
|
||||
current_image = processed.images[0]
|
||||
else:
|
||||
current_image = Image.open(prompt_images[min(k for k in prompt_images.keys() if k >= 0)]).resize(
|
||||
(width, height), resample=Image.LANCZOS
|
||||
)
|
||||
|
||||
# if custom_exit_image and ((i + 1) == num_outpainting_steps):
|
||||
# mask_width = 4 # fade out whole interpol
|
||||
# mask_height =4 #
|
||||
# mask_width = width*(20//30) # fade out whole interpol
|
||||
# mask_height = height*(20//30) #
|
||||
# else:
|
||||
mask_width = math.trunc(width / 4) # was initially 512px => 128px
|
||||
mask_height = math.trunc(height / 4) # was initially 512px => 128px
|
||||
|
||||
num_interpol_frames = round(video_frame_rate * zoom_speed)
|
||||
|
||||
all_frames = []
|
||||
|
||||
if upscale_do and progress:
|
||||
progress(0, desc="upscaling inital image")
|
||||
|
||||
all_frames.append(
|
||||
do_upscaleImg(current_image, upscale_do, upscaler_name, upscale_by)
|
||||
if upscale_do
|
||||
else current_image
|
||||
)
|
||||
|
||||
load_model_from_setting("infzoom_inpainting_model", progress, "Loading Model for inpainting/img2img: " )
|
||||
|
||||
if custom_exit_image:
|
||||
extra_frames += 2
|
||||
|
||||
# setup filesystem paths
|
||||
video_file_name = "infinite_zoom_" + str(int(time.time())) + ".mp4"
|
||||
output_path = shared.opts.data.get(
|
||||
"infzoom_outpath", shared.opts.data.get("outdir_img2img_samples")
|
||||
)
|
||||
save_path = os.path.join(
|
||||
output_path, shared.opts.data.get("infzoom_outSUBpath", "infinite-zooms")
|
||||
)
|
||||
if not os.path.exists(save_path):
|
||||
os.makedirs(save_path)
|
||||
out = os.path.join(save_path, video_file_name)
|
||||
|
||||
for i in range(num_outpainting_steps + extra_frames):
|
||||
print_out = (
|
||||
"Outpaint step: "
|
||||
+ str(i + 1)
|
||||
+ " / "
|
||||
+ str(num_outpainting_steps + extra_frames)
|
||||
+ " Seed: "
|
||||
+ str(current_seed)
|
||||
)
|
||||
print(print_out)
|
||||
if progress:
|
||||
progress(((i + 1) / num_outpainting_steps), desc=print_out)
|
||||
|
||||
if custom_exit_image and ((i + 1) == num_outpainting_steps):
|
||||
mask_width=round(width*maskwidth_slider)
|
||||
mask_height=round(height*maskheight_slider)
|
||||
|
||||
# 30 fps@ maskw 0.25 => 30
|
||||
# normalize to default speed of 30 fps for 0.25 mask factor
|
||||
num_interpol_frames = round(num_interpol_frames * (1 + (max(maskheight_slider,maskwidth_slider)/0.5) * exitgamma))
|
||||
|
||||
prev_image_fix = current_image
|
||||
prev_image = shrink_and_paste_on_blank(current_image, mask_width, mask_height)
|
||||
current_image = prev_image
|
||||
|
||||
# create mask (black image with white mask_width width edges)
|
||||
mask_image = np.array(current_image)[:, :, 3]
|
||||
mask_image = Image.fromarray(255 - mask_image).convert("RGB")
|
||||
|
||||
# inpainting step
|
||||
current_image = current_image.convert("RGB")
|
||||
|
||||
# Custom and specified images work like keyframes
|
||||
if custom_exit_image and (i + 1) >= (num_outpainting_steps + extra_frames):
|
||||
current_image = custom_exit_image.resize(
|
||||
(width, height), resample=Image.LANCZOS
|
||||
)
|
||||
print("using Custom Exit Image")
|
||||
else:
|
||||
if prompt_images[max(k for k in prompt_images.keys() if k <= (i + 1))] == "":
|
||||
processed, current_seed = renderImg2Img(
|
||||
prompts[max(k for k in prompts.keys() if k <= (i + 1))],
|
||||
negative_prompt,
|
||||
sampler,
|
||||
num_inference_steps,
|
||||
guidance_scale,
|
||||
current_seed,
|
||||
width,
|
||||
height,
|
||||
current_image,
|
||||
mask_image,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
)
|
||||
current_image = processed.images[0]
|
||||
# only paste previous image when generating a new image
|
||||
current_image.paste(prev_image, mask=prev_image)
|
||||
else:
|
||||
current_image = Image.open(prompt_images[max(k for k in prompt_images.keys() if k <= (i + 1))]).resize(
|
||||
(width, height), resample=Image.LANCZOS
|
||||
)
|
||||
|
||||
|
||||
|
||||
# interpolation steps between 2 inpainted images (=sequential zoom and crop)
|
||||
for j in range(num_interpol_frames - 1):
|
||||
interpol_image = current_image
|
||||
|
||||
interpol_width = round(
|
||||
(
|
||||
1
|
||||
- (1 - 2 * mask_width / width)
|
||||
** (1 - (j + 1) / num_interpol_frames)
|
||||
)
|
||||
* width
|
||||
/ 2
|
||||
)
|
||||
|
||||
interpol_height = round(
|
||||
(
|
||||
1
|
||||
- (1 - 2 * mask_height / height)
|
||||
** (1 - (j + 1) / num_interpol_frames)
|
||||
)
|
||||
* height
|
||||
/ 2
|
||||
)
|
||||
|
||||
interpol_image = interpol_image.crop(
|
||||
(
|
||||
interpol_width,
|
||||
interpol_height,
|
||||
width - interpol_width,
|
||||
height - interpol_height,
|
||||
)
|
||||
)
|
||||
|
||||
interpol_image = interpol_image.resize((width, height))
|
||||
|
||||
# paste the higher resolution previous image in the middle to avoid drop in quality caused by zooming
|
||||
interpol_width2 = round(
|
||||
(1 - (width - 2 * mask_width) / (width - 2 * interpol_width))
|
||||
/ 2
|
||||
* width
|
||||
)
|
||||
|
||||
interpol_height2 = round(
|
||||
(1 - (height - 2 * mask_height) / (height - 2 * interpol_height))
|
||||
/ 2
|
||||
* height
|
||||
)
|
||||
|
||||
if custom_exit_image and ((i + 1) == num_outpainting_steps):
|
||||
opacity = 1 - ((j+1)/num_interpol_frames )
|
||||
else: opacity = 1
|
||||
|
||||
prev_image_fix_crop = shrink_and_paste_on_blank(
|
||||
prev_image_fix, interpol_width2, interpol_height2,
|
||||
opacity=opacity
|
||||
)
|
||||
|
||||
interpol_image.paste(prev_image_fix_crop, mask=prev_image_fix_crop)
|
||||
|
||||
# exit image: from now we see the last prompt on the exit image
|
||||
if custom_exit_image and ((i + 1) == num_outpainting_steps):
|
||||
|
||||
mask_img = Image.new("L", (width,height), 0)
|
||||
in_center_x = interpol_image.width/2
|
||||
in_center_y = interpol_image.height/2
|
||||
|
||||
# Draw a circular brush on the mask image with 64px diameter and 8px softness
|
||||
draw = ImageDraw.Draw(mask_img)
|
||||
brush_size = 64
|
||||
brush_softness = 8
|
||||
brush = Image.new("L", (brush_size, brush_size), 255)
|
||||
draw_brush = ImageDraw.Draw(brush)
|
||||
draw_brush.ellipse((brush_softness, brush_softness, brush_size-brush_softness, brush_size-brush_softness), fill=255, outline=None)
|
||||
brush = brush.filter(ImageFilter.GaussianBlur(radius=brush_softness))
|
||||
brush_width, brush_height = brush.size
|
||||
|
||||
# Draw the rectangular frame on the mask image using the circular brush
|
||||
frame_width = width-2*interpol_width2
|
||||
frame_height = height-2*interpol_height2
|
||||
frame_left = in_center_x - (frame_width // 2)
|
||||
frame_top = in_center_y - (frame_height // 2)
|
||||
frame_right = frame_left + frame_width
|
||||
frame_bottom = frame_top + frame_height
|
||||
draw.ellipse((frame_left, frame_top, frame_left+brush_width, frame_top+brush_height), fill=255, outline=None)
|
||||
draw.ellipse((frame_right-brush_width, frame_top, frame_right, frame_top+brush_height), fill=255, outline=None)
|
||||
draw.ellipse((frame_left, frame_bottom-brush_height, frame_left+brush_width, frame_bottom), fill=255, outline=None)
|
||||
draw.ellipse((frame_right-brush_width, frame_bottom-brush_height, frame_right, frame_bottom), fill=255, outline=None)
|
||||
|
||||
draw.rectangle((max(0,frame_left-brush_size/2), max(0,frame_top+brush_size/2), max(0,frame_right-brush_size/2), max(0,frame_bottom-brush_size/2)), fill=255)
|
||||
|
||||
# inner rect, now we have a bordermask
|
||||
draw.rectangle((max(0,frame_left+brush_size/2), max(0,frame_top-brush_size/2), max(0,frame_right+brush_size/2), max(0,frame_bottom+brush_size/2)), fill=0)
|
||||
|
||||
# Blur the mask image to soften the edges
|
||||
#mask_img = mask_img.filter(ImageFilter.GaussianBlur(radius=8))
|
||||
#mask_img = ImageOps.invert(mask_img)
|
||||
#mask_img.save(output_path+os.pathsep+"Mask"+str(int(time.time()))+".png")
|
||||
"""processed, newseed = renderImg2Img(
|
||||
prompts[max(k for k in prompts.keys() if k <= i)],
|
||||
negative_prompt,
|
||||
sampler,
|
||||
num_inference_steps,
|
||||
guidance_scale,
|
||||
current_seed,
|
||||
width,
|
||||
height,
|
||||
interpol_image,
|
||||
mask_img,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
)
|
||||
#interpol_image = processed.images[0]
|
||||
"""
|
||||
|
||||
if upscale_do and progress:
|
||||
progress(((i + 1) / num_outpainting_steps), desc="upscaling interpol")
|
||||
|
||||
all_frames.append(
|
||||
do_upscaleImg(interpol_image, upscale_do, upscalerinterpol_name, upscale_by)
|
||||
if upscale_do
|
||||
else interpol_image
|
||||
)
|
||||
|
||||
if upscale_do and progress:
|
||||
progress(((i + 1) / num_outpainting_steps), desc="upscaling current")
|
||||
|
||||
all_frames.append(
|
||||
do_upscaleImg(current_image, upscale_do, upscaler_name, upscale_by)
|
||||
if upscale_do
|
||||
else current_image
|
||||
)
|
||||
|
||||
write_video(
|
||||
out,
|
||||
all_frames,
|
||||
video_frame_rate,
|
||||
video_zoom_mode,
|
||||
int(video_start_frame_dupe_amount),
|
||||
int(video_last_frame_dupe_amount),
|
||||
)
|
||||
|
||||
return (
|
||||
out,
|
||||
processed.images,
|
||||
processed.js(),
|
||||
plaintext_to_html(processed.info),
|
||||
plaintext_to_html(""),
|
||||
)
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
from modules.processing import (
|
||||
process_images,
|
||||
StableDiffusionProcessingTxt2Img,
|
||||
StableDiffusionProcessingImg2Img,
|
||||
)
|
||||
import modules.shared as shared
|
||||
|
||||
|
||||
def renderTxt2Img(
|
||||
prompt, negative_prompt, sampler, steps, cfg_scale, seed, width, height
|
||||
):
|
||||
processed = None
|
||||
p = StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
outpath_samples=shared.opts.outdir_txt2img_samples,
|
||||
outpath_grids=shared.opts.outdir_txt2img_grids,
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
seed=seed,
|
||||
sampler_name=sampler,
|
||||
n_iter=1,
|
||||
steps=steps,
|
||||
cfg_scale=cfg_scale,
|
||||
width=width,
|
||||
height=height,
|
||||
)
|
||||
processed = process_images(p)
|
||||
newseed = p.seed
|
||||
return processed, newseed
|
||||
|
||||
|
||||
def renderImg2Img(
|
||||
prompt,
|
||||
negative_prompt,
|
||||
sampler,
|
||||
steps,
|
||||
cfg_scale,
|
||||
seed,
|
||||
width,
|
||||
height,
|
||||
init_image,
|
||||
mask_image,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
):
|
||||
processed = None
|
||||
|
||||
p = StableDiffusionProcessingImg2Img(
|
||||
sd_model=shared.sd_model,
|
||||
outpath_samples=shared.opts.outdir_img2img_samples,
|
||||
outpath_grids=shared.opts.outdir_img2img_grids,
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
seed=seed,
|
||||
sampler_name=sampler,
|
||||
n_iter=1,
|
||||
steps=steps,
|
||||
cfg_scale=cfg_scale,
|
||||
width=width,
|
||||
height=height,
|
||||
init_images=[init_image],
|
||||
denoising_strength=inpainting_denoising_strength,
|
||||
mask_blur=inpainting_mask_blur,
|
||||
inpainting_fill=inpainting_fill_mode,
|
||||
inpaint_full_res=inpainting_full_res,
|
||||
inpaint_full_res_padding=inpainting_padding,
|
||||
mask=mask_image,
|
||||
)
|
||||
# p.latent_mask = Image.new("RGB", (p.width, p.height), "white")
|
||||
|
||||
processed = process_images(p)
|
||||
newseed = p.seed
|
||||
return processed, newseed
|
||||
|
|
@ -0,0 +1,96 @@
|
|||
import modules.shared as shared
|
||||
from .static_variables import default_prompt
|
||||
import gradio as gr
|
||||
|
||||
|
||||
def on_ui_settings():
|
||||
section = ("infinite-zoom", "Infinite Zoom")
|
||||
|
||||
shared.opts.add_option(
|
||||
"outputs"
|
||||
"infzoom_outpath",
|
||||
shared.OptionInfo(
|
||||
"",
|
||||
"Path where to store your infinite video. Default is Outputs",
|
||||
gr.Textbox,
|
||||
{"interactive": True},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_outSUBpath",
|
||||
shared.OptionInfo(
|
||||
"infinite-zooms",
|
||||
"Which subfolder name to be created in the outpath. Default is 'infinite-zooms'",
|
||||
gr.Textbox,
|
||||
{"interactive": True},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_outsizeW",
|
||||
shared.OptionInfo(
|
||||
512,
|
||||
"Default width of your video",
|
||||
gr.Slider,
|
||||
{"minimum": 16, "maximum": 2048, "step": 16},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_outsizeH",
|
||||
shared.OptionInfo(
|
||||
512,
|
||||
"Default height your video",
|
||||
gr.Slider,
|
||||
{"minimum": 16, "maximum": 2048, "step": 16},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_ffprobepath",
|
||||
shared.OptionInfo(
|
||||
"",
|
||||
"Writing videos has dependency to an existing FFPROBE executable on your machine. D/L here (https://github.com/BtbN/FFmpeg-Builds/releases) your OS variant and point to your installation path",
|
||||
gr.Textbox,
|
||||
{"interactive": True},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_txt2img_model",
|
||||
shared.OptionInfo(
|
||||
None,
|
||||
"Name of your desired model to render keyframes (txt2img)",
|
||||
gr.Dropdown,
|
||||
lambda: {"choices": shared.list_checkpoint_tiles()},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_inpainting_model",
|
||||
shared.OptionInfo(
|
||||
None,
|
||||
"Name of your desired inpaint model (img2img-inpaint). Default is vanilla sd-v1-5-inpainting.ckpt ",
|
||||
gr.Dropdown,
|
||||
lambda: {"choices": shared.list_checkpoint_tiles()},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
||||
shared.opts.add_option(
|
||||
"infzoom_defPrompt",
|
||||
shared.OptionInfo(
|
||||
default_prompt,
|
||||
"Default prompt-setup to start with'",
|
||||
gr.Code,
|
||||
{"interactive": True, "language": "json"},
|
||||
section=section,
|
||||
),
|
||||
)
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
import os
|
||||
from modules import scripts
|
||||
import modules.sd_samplers
|
||||
|
||||
default_prompt = """
|
||||
{
|
||||
"prompts":{
|
||||
"headers":["outpaint steps","prompt","image location"],
|
||||
"data":[
|
||||
[0,"Huge spectacular Waterfall in a dense tropical forest,epic perspective,(vegetation overgrowth:1.3)(intricate, ornamentation:1.1),(baroque:1.1), fantasy, (realistic:1) digital painting , (magical,mystical:1.2) , (wide angle shot:1.4), (landscape composed:1.2)(medieval:1.1), divine,cinematic,(tropical forest:1.4),(river:1.3)mythology,india, volumetric lighting, Hindu ,epic, Alex Horley Wenjun Lin greg rutkowski Ruan Jia (Wayne Barlowe:1.2) <lora:epiNoiseoffset_v2:0.6> ","C:\\path\\to\\image.png"]
|
||||
]
|
||||
},
|
||||
"negPrompt":"frames, borderline, text, character, duplicate, error, out of frame, watermark, low quality, ugly, deformed, blur bad-artist"
|
||||
}
|
||||
"""
|
||||
available_samplers = [
|
||||
s.name for s in modules.sd_samplers.samplers if "UniPc" not in s.name
|
||||
]
|
||||
|
||||
empty_prompt = (
|
||||
'{"prompts":{"data":[],"headers":["outpaint steps","prompt","image location"]},"negPrompt":""}'
|
||||
)
|
||||
|
||||
invalid_prompt = {
|
||||
"prompts": {
|
||||
"data": [[0, "Your prompt-json is invalid, please check Settings",""]],
|
||||
"headers": ["outpaint steps", "prompt","image location"],
|
||||
},
|
||||
"negPrompt": "Invalid prompt-json",
|
||||
}
|
||||
current_script_dir = scripts.basedir().split(os.sep)[
|
||||
-2:
|
||||
] # contains install and our extension foldername
|
||||
jsonprompt_schemafile = (
|
||||
current_script_dir[0]
|
||||
+ "/"
|
||||
+ current_script_dir[1]
|
||||
+ "/iz_helpers/promptschema.json"
|
||||
)
|
||||
|
|
@ -0,0 +1,289 @@
|
|||
import json
|
||||
import gradio as gr
|
||||
from .run import create_zoom
|
||||
import modules.shared as shared
|
||||
from webui import wrap_gradio_gpu_call
|
||||
from modules.ui import create_output_panel
|
||||
from .static_variables import (
|
||||
default_prompt,
|
||||
empty_prompt,
|
||||
invalid_prompt,
|
||||
available_samplers,
|
||||
)
|
||||
from .helpers import validatePromptJson_throws, putPrompts, clearPrompts
|
||||
|
||||
|
||||
def on_ui_tabs():
|
||||
with gr.Blocks(analytics_enabled=False) as infinite_zoom_interface:
|
||||
gr.HTML(
|
||||
"""
|
||||
<p style="text-align: center;">
|
||||
<a target="_blank" href="https://github.com/v8hid/infinite-zoom-automatic1111-webui"><img src="https://img.shields.io/static/v1?label=github&message=repository&color=blue&style=flat&logo=github&logoColor=white" style="display: inline;" alt="GitHub Repo"/></a>
|
||||
<a href="https://discord.gg/v2nHqSrWdW"><img src="https://img.shields.io/discord/1095469311830806630?color=blue&label=discord&logo=discord&logoColor=white" style="display: inline;" alt="Discord server"></a>
|
||||
</p>
|
||||
|
||||
"""
|
||||
)
|
||||
with gr.Row():
|
||||
generate_btn = gr.Button(value="Generate video", variant="primary")
|
||||
interrupt = gr.Button(value="Interrupt", elem_id="interrupt_training")
|
||||
with gr.Row():
|
||||
with gr.Column(scale=1, variant="panel"):
|
||||
with gr.Tab("Main"):
|
||||
main_outpaint_steps = gr.Slider(
|
||||
minimum=1,
|
||||
maximum=100,
|
||||
step=1,
|
||||
value=8,
|
||||
label="Total Outpaint Steps",
|
||||
info="The more it is, the longer your videos will be",
|
||||
)
|
||||
|
||||
# safe reading json prompt
|
||||
pr = shared.opts.data.get("infzoom_defPrompt", default_prompt)
|
||||
if not pr:
|
||||
pr = empty_prompt
|
||||
try:
|
||||
jpr = json.loads(pr)
|
||||
validatePromptJson_throws(jpr)
|
||||
except Exception:
|
||||
jpr = invalid_prompt
|
||||
|
||||
main_prompts = gr.Dataframe(
|
||||
type="array",
|
||||
headers=["outpaint step", "prompt", "image location"],
|
||||
datatype=["number", "str", "str"],
|
||||
row_count=1,
|
||||
col_count=(3, "fixed"),
|
||||
value=jpr["prompts"],
|
||||
wrap=True,
|
||||
)
|
||||
|
||||
main_negative_prompt = gr.Textbox(
|
||||
value=jpr["negPrompt"], label="Negative Prompt"
|
||||
)
|
||||
|
||||
# these button will be moved using JS unde the dataframe view as small ones
|
||||
exportPrompts_button = gr.Button(
|
||||
value="Export prompts",
|
||||
variant="secondary",
|
||||
elem_classes="sm infzoom_tab_butt",
|
||||
elem_id="infzoom_exP_butt",
|
||||
)
|
||||
importPrompts_button = gr.UploadButton(
|
||||
label="Import prompts",
|
||||
variant="secondary",
|
||||
elem_classes="sm infzoom_tab_butt",
|
||||
elem_id="infzoom_imP_butt",
|
||||
)
|
||||
exportPrompts_button.click(
|
||||
None,
|
||||
_js="exportPrompts",
|
||||
inputs=[main_prompts, main_negative_prompt],
|
||||
outputs=None,
|
||||
)
|
||||
importPrompts_button.upload(
|
||||
fn=putPrompts,
|
||||
outputs=[main_prompts, main_negative_prompt],
|
||||
inputs=[importPrompts_button],
|
||||
)
|
||||
|
||||
clearPrompts_button = gr.Button(
|
||||
value="Clear prompts",
|
||||
variant="secondary",
|
||||
elem_classes="sm infzoom_tab_butt",
|
||||
elem_id="infzoom_clP_butt",
|
||||
)
|
||||
clearPrompts_button.click(
|
||||
fn=clearPrompts,
|
||||
inputs=[],
|
||||
outputs=[main_prompts, main_negative_prompt],
|
||||
)
|
||||
with gr.Row():
|
||||
seed = gr.Number(
|
||||
label="Seed", value=-1, precision=0, interactive=True
|
||||
)
|
||||
main_sampler = gr.Dropdown(
|
||||
label="Sampler",
|
||||
choices=available_samplers,
|
||||
value="Euler a",
|
||||
type="value",
|
||||
)
|
||||
with gr.Row():
|
||||
main_width = gr.Slider(
|
||||
minimum=16,
|
||||
maximum=2048,
|
||||
value=shared.opts.data.get("infzoom_outsizeW", 512),
|
||||
step=16,
|
||||
label="Output Width",
|
||||
)
|
||||
main_height = gr.Slider(
|
||||
minimum=16,
|
||||
maximum=2048,
|
||||
value=shared.opts.data.get("infzoom_outsizeH", 512),
|
||||
step=16,
|
||||
label="Output Height",
|
||||
)
|
||||
with gr.Row():
|
||||
main_guidance_scale = gr.Slider(
|
||||
minimum=0.1,
|
||||
maximum=15,
|
||||
step=0.1,
|
||||
value=7,
|
||||
label="Guidance Scale",
|
||||
)
|
||||
sampling_step = gr.Slider(
|
||||
minimum=1,
|
||||
maximum=100,
|
||||
step=1,
|
||||
value=50,
|
||||
label="Sampling Steps for each outpaint",
|
||||
)
|
||||
with gr.Row():
|
||||
init_image = gr.Image(type="pil", label="custom initial image")
|
||||
exit_image = gr.Image(type="pil", label="custom exit image")
|
||||
|
||||
with gr.Row():
|
||||
batchcount_slider = gr.Slider(
|
||||
minimum=1,
|
||||
maximum=25,
|
||||
value=shared.opts.data.get("infzoom_batchcount", 1),
|
||||
step=1,
|
||||
label="Batch Count",
|
||||
)
|
||||
with gr.Accordion("I know what I am doing!", open=False):
|
||||
gamma_slider = gr.Slider(value=0.0,minimum=0.0,maximum=10,label="Exit Image speed - Gamma")
|
||||
maskwidth_slider = gr.Slider(value=0.25,minimum=0.1,maximum=0.49,label="MaskWidth ratio ")
|
||||
maskheight_slider = gr.Slider(value=0.25,minimum=0.1,maximum=0.49,label="MaskHeight ratio")
|
||||
|
||||
with gr.Tab("Video"):
|
||||
video_frame_rate = gr.Slider(
|
||||
label="Frames per second",
|
||||
value=30,
|
||||
minimum=1,
|
||||
maximum=60,
|
||||
)
|
||||
video_zoom_mode = gr.Radio(
|
||||
label="Zoom mode",
|
||||
choices=["Zoom-out", "Zoom-in"],
|
||||
value="Zoom-out",
|
||||
type="index",
|
||||
)
|
||||
video_start_frame_dupe_amount = gr.Slider(
|
||||
label="number of start frame dupe",
|
||||
info="Frames to freeze at the start of the video",
|
||||
value=0,
|
||||
minimum=1,
|
||||
maximum=60,
|
||||
)
|
||||
video_last_frame_dupe_amount = gr.Slider(
|
||||
label="number of last frame dupe",
|
||||
info="Frames to freeze at the end of the video",
|
||||
value=0,
|
||||
minimum=1,
|
||||
maximum=60,
|
||||
)
|
||||
video_zoom_speed = gr.Slider(
|
||||
label="Zoom Speed",
|
||||
value=1.0,
|
||||
minimum=0.1,
|
||||
maximum=20.0,
|
||||
step=0.1,
|
||||
info="Zoom speed in seconds (higher values create slower zoom)",
|
||||
)
|
||||
|
||||
with gr.Tab("Outpaint"):
|
||||
inpainting_denoising_strength = gr.Slider(
|
||||
label="Denoising Strength", minimum=0.75, maximum=1, value=1
|
||||
)
|
||||
inpainting_mask_blur = gr.Slider(
|
||||
label="Mask Blur", minimum=0, maximum=64, value=0
|
||||
)
|
||||
inpainting_fill_mode = gr.Radio(
|
||||
label="Masked content",
|
||||
choices=["fill", "original", "latent noise", "latent nothing"],
|
||||
value="latent noise",
|
||||
type="index",
|
||||
)
|
||||
inpainting_full_res = gr.Checkbox(label="Inpaint Full Resolution")
|
||||
inpainting_padding = gr.Slider(
|
||||
label="masked padding", minimum=0, maximum=256, value=0
|
||||
)
|
||||
|
||||
with gr.Tab("Post proccess"):
|
||||
upscale_do = gr.Checkbox(False, label="Enable Upscale")
|
||||
with gr.Row():
|
||||
upscaler_name = gr.Dropdown(
|
||||
label="Upscaler for keyframes (txt2img;inpaint)",
|
||||
elem_id="infZ_upscaler",
|
||||
choices=[x.name for x in shared.sd_upscalers],
|
||||
value=shared.sd_upscalers[0].name,
|
||||
)
|
||||
|
||||
upscalerinterpol_name = gr.Dropdown(
|
||||
label="Upscaler for interpolation",
|
||||
elem_id="infZ_upscaler_interpol",
|
||||
choices=[x.name for x in shared.sd_upscalers],
|
||||
value=shared.sd_upscalers[0].name,
|
||||
)
|
||||
|
||||
upscale_by = gr.Slider(
|
||||
label="Upscale by factor", minimum=1, maximum=8, value=1
|
||||
)
|
||||
with gr.Accordion("Help", open=False):
|
||||
gr.Markdown(
|
||||
"""# Performance critical
|
||||
Depending on amount of frames and which upscaler you choose it might took a long time to render.
|
||||
Our best experience and trade-off is the R-ESRGAN 4x upscaler.
|
||||
"""
|
||||
)
|
||||
|
||||
with gr.Column(scale=1, variant="compact"):
|
||||
output_video = gr.Video(label="Output").style(width=512, height=512)
|
||||
(
|
||||
out_image,
|
||||
generation_info,
|
||||
html_info,
|
||||
html_log,
|
||||
) = create_output_panel(
|
||||
"infinite-zoom", shared.opts.outdir_img2img_samples
|
||||
)
|
||||
generate_btn.click(
|
||||
fn=wrap_gradio_gpu_call(create_zoom, extra_outputs=[None, "", ""]),
|
||||
inputs=[
|
||||
main_prompts,
|
||||
main_negative_prompt,
|
||||
main_outpaint_steps,
|
||||
main_guidance_scale,
|
||||
sampling_step,
|
||||
init_image,
|
||||
exit_image,
|
||||
video_frame_rate,
|
||||
video_zoom_mode,
|
||||
video_start_frame_dupe_amount,
|
||||
video_last_frame_dupe_amount,
|
||||
inpainting_denoising_strength,
|
||||
inpainting_mask_blur,
|
||||
inpainting_fill_mode,
|
||||
inpainting_full_res,
|
||||
inpainting_padding,
|
||||
video_zoom_speed,
|
||||
seed,
|
||||
main_width,
|
||||
main_height,
|
||||
batchcount_slider,
|
||||
main_sampler,
|
||||
upscale_do,
|
||||
upscaler_name,
|
||||
upscalerinterpol_name,
|
||||
upscale_by,
|
||||
gamma_slider,
|
||||
maskwidth_slider,
|
||||
maskheight_slider,
|
||||
|
||||
],
|
||||
outputs=[output_video, out_image, generation_info, html_info, html_log],
|
||||
)
|
||||
interrupt.click(fn=lambda: shared.state.interrupt(), inputs=[], outputs=[])
|
||||
infinite_zoom_interface.queue()
|
||||
return [(infinite_zoom_interface, "Infinite Zoom", "iz_interface")]
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue