diff --git a/.gitignore b/.gitignore
index 876e20e..2638864 100644
--- a/.gitignore
+++ b/.gitignore
@@ -129,3 +129,4 @@ dmypy.json
.pyre/
.vscode/settings.json
.DS_Store
+/.vs
diff --git a/iz_helpers/__init__.py b/iz_helpers/__init__.py
index 8798cf1..19c0211 100644
--- a/iz_helpers/__init__.py
+++ b/iz_helpers/__init__.py
@@ -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
diff --git a/iz_helpers/extra.py b/iz_helpers/extra.py
new file mode 100644
index 0000000..e69de29
diff --git a/iz_helpers/helpers.py b/iz_helpers/helpers.py
new file mode 100644
index 0000000..c7b110e
--- /dev/null
+++ b/iz_helpers/helpers.py
@@ -0,0 +1,126 @@
+import math
+import os
+import modules.shared as shared
+import modules.sd_models
+import gradio as gr
+from scripts import postprocessing_upscale
+from .prompt_util import readJsonPrompt
+import asyncio
+
+
+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
+
+async def showGradioErrorAsync(txt, delay=1):
+ await asyncio.sleep(delay) # sleep for 1 second
+ raise gr.Error(txt)
+
+def putPrompts(files):
+ try:
+ with open(files.name, "r") as f:
+ file_contents = f.read()
+
+ data = readJsonPrompt(file_contents,False)
+ return [
+ gr.Textbox.update(data["prePrompt"]),
+ gr.DataFrame.update(data["prompts"]),
+ gr.Textbox.update(data["postPrompt"]),
+ gr.Textbox.update(data["negPrompt"])
+ ]
+
+ except Exception:
+ print(
+ "[InfiniteZoom:] Loading your prompt failed. It seems to be invalid. Your prompt table is preserved."
+ )
+
+ # error only be shown with raise, so ui gets broken.
+ #asyncio.run(showGradioErrorAsync("Loading your prompts failed. It seems to be invalid. Your prompt table has been preserved.",5))
+
+ return [gr.Textbox.update(), gr.DataFrame.update(), gr.Textbox.update(),gr.Textbox.update()]
+
+
+def clearPrompts():
+ return [
+ gr.DataFrame.update(value=[[0, "Infinite Zoom. Start over"]]),
+ gr.Textbox.update(""),
+ gr.Textbox.update(""),
+ gr.Textbox.update("")
+ ]
diff --git a/iz_helpers/prompt_util.py b/iz_helpers/prompt_util.py
new file mode 100644
index 0000000..4ef5433
--- /dev/null
+++ b/iz_helpers/prompt_util.py
@@ -0,0 +1,67 @@
+import json
+from jsonschema import validate
+
+from .static_variables import (
+ empty_prompt,
+ invalid_prompt,
+ jsonprompt_schemafile,
+ promptTableHeaders
+)
+
+def completeOptionals(j):
+ if isinstance(j, dict):
+ # Remove header information, user dont pimp our ui
+ if "prompts" in j:
+ if "headers" in j["prompts"]:
+ del j["prompts"]["headers"]
+ j["prompts"]["headers"]=promptTableHeaders
+
+ if "negPrompt" not in j:
+ j["negPrompt"]=""
+
+ if "prePrompt" not in j:
+ if "commonPromptPrefix" in j:
+ j["prePrompt"]=j["commonPromptPrefix"]
+ else:
+ j["prePrompt"]=""
+
+ if "postPrompt" not in j:
+ if "commonPromptSuffix" in j:
+ j["postPrompt"]=j["commonPromptSuffix"]
+ else:
+ j["postPrompt"]=""
+
+ return j
+
+
+def validatePromptJson_throws(data):
+ with open(jsonprompt_schemafile, "r") as s:
+ schema = json.load(s)
+ try:
+ validate(instance=data, schema=schema)
+
+ except Exception:
+ raise Exception("Your prompts are not schema valid.")
+
+ return completeOptionals(data)
+
+
+def readJsonPrompt(txt, returnFailPrompt=False):
+ if not txt:
+ return empty_prompt
+
+ try:
+ jpr = json.loads(txt)
+ except Exception:
+ if returnFailPrompt:
+ print (f"Infinite Zoom: Corrupted Json structure: {txt[:24]} ...")
+ return invalid_prompt
+ raise (f"Infinite Zoom: Corrupted Json structure: {txt[:24]} ...")
+
+ try:
+ return validatePromptJson_throws(jpr)
+ except Exception:
+ if returnFailPrompt:
+ return invalid_prompt
+ pass
+
diff --git a/iz_helpers/promptschema.json b/iz_helpers/promptschema.json
new file mode 100644
index 0000000..ec513e0
--- /dev/null
+++ b/iz_helpers/promptschema.json
@@ -0,0 +1,60 @@
+{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "$id": "1.1",
+ "type": "object",
+ "properties": {
+ "prompts": {
+ "type": "object",
+ "properties": {
+ "data": {
+ "type": "array",
+ "items": {
+ "type": "array",
+ "items": [
+ {
+ "oneOf": [
+ {
+ "type": "integer",
+ "minimum": 0
+ },
+ {
+ "type": "string"
+ }
+ ]
+ },
+ {
+ "type": "string"
+ }
+ ],
+ "minItems": 0,
+ "maxItems": 999,
+ "uniqueItems": false
+ },
+ "minItems": 0
+ },
+ "headers": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ },
+ "minItems": 2
+ }
+ },
+ "required": [
+ "data"
+ ]
+ },
+ "negPrompt": {
+ "type": "string"
+ },
+ "prePrompt": {
+ "type": "string"
+ },
+ "postPrompt": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "prompts"
+ ]
+}
\ No newline at end of file
diff --git a/iz_helpers/run.py b/iz_helpers/run.py
new file mode 100644
index 0000000..d224af5
--- /dev/null
+++ b/iz_helpers/run.py
@@ -0,0 +1,512 @@
+import math, time, os
+import numpy as np
+from PIL import Image, ImageFilter, ImageDraw
+from modules.ui import plaintext_to_html
+import modules.shared as shared
+from modules.paths_internal import script_path
+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 crop_fethear_ellipse(image, feather_margin=30, width_offset=0, height_offset=0):
+ # Create a blank mask image with the same size as the original image
+ mask = Image.new("L", image.size, 0)
+ draw = ImageDraw.Draw(mask)
+
+ # Calculate the ellipse's bounding box
+ ellipse_box = (
+ width_offset,
+ height_offset,
+ image.width - width_offset,
+ image.height - height_offset,
+ )
+
+ # Draw the ellipse on the mask
+ draw.ellipse(ellipse_box, fill=255)
+
+ # Apply the mask to the original image
+ result = Image.new("RGBA", image.size)
+ result.paste(image, mask=mask)
+
+ # Crop the resulting image to the ellipse's bounding box
+ cropped_image = result.crop(ellipse_box)
+
+ # Create a new mask image with a black background (0)
+ mask = Image.new("L", cropped_image.size, 0)
+ draw = ImageDraw.Draw(mask)
+
+ # Draw an ellipse on the mask image
+ draw.ellipse(
+ (
+ 0 + feather_margin,
+ 0 + feather_margin,
+ cropped_image.width - feather_margin,
+ cropped_image.height - feather_margin,
+ ),
+ fill=255,
+ outline=0,
+ )
+
+ # Apply a Gaussian blur to the mask image
+ mask = mask.filter(ImageFilter.GaussianBlur(radius=feather_margin / 2))
+ cropped_image.putalpha(mask)
+ res = Image.new(cropped_image.mode, (image.width, image.height))
+ paste_pos = (
+ int((res.width - cropped_image.width) / 2),
+ int((res.height - cropped_image.height) / 2),
+ )
+ res.paste(cropped_image, paste_pos)
+
+ return res
+
+
+def outpaint_steps(
+ width,
+ height,
+ common_prompt_pre,
+ common_prompt_suf,
+ prompts,
+ negative_prompt,
+ seed,
+ sampler,
+ num_inference_steps,
+ guidance_scale,
+ inpainting_denoising_strength,
+ inpainting_mask_blur,
+ inpainting_fill_mode,
+ inpainting_full_res,
+ inpainting_padding,
+ init_img,
+ outpaint_steps,
+ out_config,
+ mask_width,
+ mask_height,
+ custom_exit_image,
+ frame_correction=True, # TODO: add frame_Correction in UI
+):
+ main_frames = [init_img.convert("RGB")]
+
+ for i in range(outpaint_steps):
+ print_out = (
+ "Outpaint step: "
+ + str(i + 1)
+ + " / "
+ + str(outpaint_steps)
+ + " Seed: "
+ + str(seed)
+ )
+ print(print_out)
+ current_image = main_frames[-1]
+ current_image = shrink_and_paste_on_blank(
+ current_image, mask_width, mask_height
+ )
+
+ mask_image = np.array(current_image)[:, :, 3]
+ mask_image = Image.fromarray(255 - mask_image).convert("RGB")
+ # create mask (black image with white mask_width width edges)
+
+ if custom_exit_image and ((i + 1) == outpaint_steps):
+ current_image = custom_exit_image.resize(
+ (width, height), resample=Image.LANCZOS
+ )
+ main_frames.append(current_image.convert("RGB"))
+ # print("using Custom Exit Image")
+ save2Collect(current_image, out_config, f"exit_img.png")
+ else:
+ pr = prompts[max(k for k in prompts.keys() if k <= i)]
+ processed, newseed = renderImg2Img(
+ f"{common_prompt_pre}\n{pr}\n{common_prompt_suf}".strip(),
+ negative_prompt,
+ sampler,
+ num_inference_steps,
+ guidance_scale,
+ seed,
+ width,
+ height,
+ current_image,
+ mask_image,
+ inpainting_denoising_strength,
+ inpainting_mask_blur,
+ inpainting_fill_mode,
+ inpainting_full_res,
+ inpainting_padding,
+ )
+
+ if len(processed.images) > 0:
+ main_frames.append(processed.images[0].convert("RGB"))
+ save2Collect(processed.images[0], out_config, f"outpain_step_{i}.png")
+ seed = newseed
+ # TODO: seed behavior
+
+ if frame_correction and inpainting_mask_blur > 0:
+ corrected_frame = crop_inner_image(
+ main_frames[i + 1], mask_width, mask_height
+ )
+
+ enhanced_img = crop_fethear_ellipse(
+ main_frames[i],
+ 30,
+ inpainting_mask_blur / 3 // 2,
+ inpainting_mask_blur / 3 // 2,
+ )
+ save2Collect(main_frames[i], out_config, f"main_frame_{i}")
+ save2Collect(enhanced_img, out_config, f"main_frame_enhanced_{i}")
+ corrected_frame.paste(enhanced_img, mask=enhanced_img)
+ main_frames[i] = corrected_frame
+ # else :TEST
+ # current_image.paste(prev_image, mask=prev_image)
+ return main_frames, processed
+
+
+def create_zoom(
+ common_prompt_pre,
+ prompts_array,
+ common_prompt_suf,
+ 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_mask_blur,
+ inpainting_fill_mode,
+ zoom_speed,
+ seed,
+ outputsizeW,
+ outputsizeH,
+ batchcount,
+ sampler,
+ upscale_do,
+ upscaler_name,
+ upscale_by,
+ inpainting_denoising_strength=1,
+ inpainting_full_res=0,
+ inpainting_padding=0,
+ progress=None,
+):
+ for i in range(batchcount):
+ print(f"Batch {i+1}/{batchcount}")
+ result = create_zoom_single(
+ common_prompt_pre,
+ prompts_array,
+ common_prompt_suf,
+ 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_mask_blur,
+ inpainting_fill_mode,
+ zoom_speed,
+ seed,
+ outputsizeW,
+ outputsizeH,
+ sampler,
+ upscale_do,
+ upscaler_name,
+ upscale_by,
+ inpainting_denoising_strength,
+ inpainting_full_res,
+ inpainting_padding,
+ progress,
+ )
+ return result
+
+
+def prepare_output_path():
+ isCollect = shared.opts.data.get("infzoom_collectAllResources", False)
+ output_path = shared.opts.data.get("infzoom_outpath", "outputs")
+
+ save_path = os.path.join(
+ output_path, shared.opts.data.get("infzoom_outSUBpath", "infinite-zooms")
+ )
+
+ if isCollect:
+ save_path = os.path.join(save_path, "iz_collect" + str(int(time.time())))
+
+ if not os.path.exists(save_path):
+ os.makedirs(save_path)
+
+ video_filename = os.path.join(
+ save_path, "infinite_zoom_" + str(int(time.time())) + ".mp4"
+ )
+
+ return {
+ "isCollect": isCollect,
+ "save_path": save_path,
+ "video_filename": video_filename,
+ }
+
+
+def save2Collect(img, out_config, name):
+ if out_config["isCollect"]:
+ img.save(f'{out_config["save_path"]}/{name}.png')
+
+
+def frame2Collect(all_frames, out_config):
+ save2Collect(all_frames[-1], out_config, f"frame_{len(all_frames)}")
+
+
+def frames2Collect(all_frames, out_config):
+ for i, f in enumerate(all_frames):
+ save2Collect(f, out_config, f"frame_{i}")
+
+
+def crop_inner_image(outpainted_img, width_offset, height_offset):
+ width, height = outpainted_img.size
+
+ center_x, center_y = int(width / 2), int(height / 2)
+
+ # Crop the image to the center
+ cropped_img = outpainted_img.crop(
+ (
+ center_x - width_offset,
+ center_y - height_offset,
+ center_x + width_offset,
+ center_y + height_offset,
+ )
+ )
+ prev_step_img = cropped_img.resize((width, height), resample=Image.LANCZOS)
+ # resized_img = resized_img.filter(ImageFilter.SHARPEN)
+
+ return prev_step_img
+
+
+def create_zoom_single(
+ common_prompt_pre,
+ prompts_array,
+ common_prompt_suf,
+ 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_mask_blur,
+ inpainting_fill_mode,
+ zoom_speed,
+ seed,
+ outputsizeW,
+ outputsizeH,
+ sampler,
+ upscale_do,
+ upscaler_name,
+ upscale_by,
+ inpainting_denoising_strength,
+ inpainting_full_res,
+ inpainting_padding,
+ progress,
+):
+ # try:
+ # if gr.Progress() is not None:
+ # progress = gr.Progress()
+ # progress(0, desc="Preparing Initial Image")
+ # except Exception:
+ # pass
+ fix_env_Path_ffprobe()
+ out_config = prepare_output_path()
+
+ prompts = {}
+
+ for x in prompts_array:
+ try:
+ key = int(x[0])
+ value = str(x[1])
+ prompts[key] = value
+ except ValueError:
+ pass
+
+ assert len(prompts_array) > 0, "prompts is empty"
+
+ 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
+
+ if custom_init_image:
+ current_image = custom_init_image.resize(
+ (width, height), resample=Image.LANCZOS
+ )
+ save2Collect(current_image, out_config, f"init_custom.png")
+
+ else:
+ load_model_from_setting(
+ "infzoom_txt2img_model", progress, "Loading Model for txt2img: "
+ )
+
+ pr = prompts[min(k for k in prompts.keys() if k >= 0)]
+ processed, newseed = renderTxt2Img(
+ f"{common_prompt_pre}\n{pr}\n{common_prompt_suf}".strip(),
+ negative_prompt,
+ sampler,
+ num_inference_steps,
+ guidance_scale,
+ current_seed,
+ width,
+ height,
+ )
+ if len(processed.images) > 0:
+ current_image = processed.images[0]
+ save2Collect(current_image, out_config, f"init_txt2img.png")
+ current_seed = newseed
+
+ 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")
+
+ load_model_from_setting(
+ "infzoom_inpainting_model", progress, "Loading Model for inpainting/img2img: "
+ )
+ main_frames, processed = outpaint_steps(
+ width,
+ height,
+ common_prompt_pre,
+ common_prompt_suf,
+ prompts,
+ negative_prompt,
+ seed,
+ sampler,
+ num_inference_steps,
+ guidance_scale,
+ inpainting_denoising_strength,
+ inpainting_mask_blur,
+ inpainting_fill_mode,
+ inpainting_full_res,
+ inpainting_padding,
+ current_image,
+ num_outpainting_steps,
+ out_config,
+ mask_width,
+ mask_height,
+ custom_exit_image,
+ )
+ all_frames.append(
+ do_upscaleImg(main_frames[0], upscale_do, upscaler_name, upscale_by)
+ if upscale_do
+ else main_frames[0]
+ )
+ for i in range(len(main_frames) - 1):
+ # interpolation steps between 2 inpainted images (=sequential zoom and crop)
+ for j in range(num_interpol_frames - 1):
+ current_image = main_frames[i + 1]
+ interpol_image = current_image
+ save2Collect(interpol_image, out_config, f"interpol_img_{i}_{j}].png")
+
+ interpol_width = math.ceil(
+ (
+ 1
+ - (1 - 2 * mask_width / width)
+ ** (1 - (j + 1) / num_interpol_frames)
+ )
+ * width
+ / 2
+ )
+
+ interpol_height = math.ceil(
+ (
+ 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))
+ save2Collect(interpol_image, out_config, f"interpol_resize_{i}_{j}.png")
+
+ # paste the higher resolution previous image in the middle to avoid drop in quality caused by zooming
+ interpol_width2 = math.ceil(
+ (1 - (width - 2 * mask_width) / (width - 2 * interpol_width))
+ / 2
+ * width
+ )
+
+ interpol_height2 = math.ceil(
+ (1 - (height - 2 * mask_height) / (height - 2 * interpol_height))
+ / 2
+ * height
+ )
+
+ prev_image_fix_crop = shrink_and_paste_on_blank(
+ main_frames[i], interpol_width2, interpol_height2
+ )
+
+ interpol_image.paste(prev_image_fix_crop, mask=prev_image_fix_crop)
+ save2Collect(interpol_image, out_config, f"interpol_prevcrop_{i}_{j}.png")
+
+ if upscale_do and progress:
+ progress(((i + 1) / num_outpainting_steps), desc="upscaling interpol")
+
+ all_frames.append(
+ do_upscaleImg(interpol_image, upscale_do, upscaler_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
+ )
+
+ frames2Collect(all_frames, out_config)
+
+ write_video(
+ out_config["video_filename"],
+ all_frames,
+ video_frame_rate,
+ video_zoom_mode,
+ int(video_start_frame_dupe_amount),
+ int(video_last_frame_dupe_amount),
+ )
+ print("Video saved in: " + os.path.join(script_path, out_config["video_filename"]))
+ return (
+ out_config["video_filename"],
+ main_frames,
+ processed.js(),
+ plaintext_to_html(processed.info),
+ plaintext_to_html(""),
+ )
diff --git a/iz_helpers/sd_helpers.py b/iz_helpers/sd_helpers.py
new file mode 100644
index 0000000..e6d5d6b
--- /dev/null
+++ b/iz_helpers/sd_helpers.py
@@ -0,0 +1,81 @@
+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)
+ # For those that use Image grids this will make sure that ffmpeg does not crash out
+ if (len(processed.images) > 1) and (processed.images[0].size[0] != processed.images[-1].size[0]):
+ processed.images.pop(0)
+ print("\nGrid image detected applying patch")
+
+ newseed = p.seed
+ return processed, newseed
diff --git a/iz_helpers/settings.py b/iz_helpers/settings.py
new file mode 100644
index 0000000..5b000c6
--- /dev/null
+++ b/iz_helpers/settings.py
@@ -0,0 +1,108 @@
+import gradio as gr
+import modules.shared as shared
+from .static_variables import default_prompt
+
+
+def on_ui_settings():
+ section = ("infinite-zoom", "Infinite Zoom")
+
+ shared.opts.add_option(
+ "infzoom_outpath",
+ shared.OptionInfo(
+ "outputs",
+ "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": [x for x in list(shared.list_checkpoint_tiles()) if "inpainting" not in x]},
+ 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": [x for x in list(shared.list_checkpoint_tiles()) if "inpainting" in x]},
+ 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,
+ ),
+ )
+
+
+ shared.opts.add_option(
+ "infzoom_collectAllResources",
+ shared.OptionInfo(
+ False,
+ "!!! Store all images (txt2img, init_image,exit_image, inpainting, interpolation) into one folder in your OUTPUT Path. Very slow, a lot of data. Dont do this on long runs !!!",
+ gr.Checkbox,
+ {"interactive": True},
+ section=section,
+ ),
+ )
+
diff --git a/iz_helpers/static_variables.py b/iz_helpers/static_variables.py
new file mode 100644
index 0000000..a54c1f5
--- /dev/null
+++ b/iz_helpers/static_variables.py
@@ -0,0 +1,51 @@
+import os
+from modules import scripts
+import modules.sd_samplers
+
+default_sampling_steps = 35
+default_sampler = "DDIM"
+default_cfg_scale = 8
+default_mask_blur = 48
+default_total_outpaints = 5
+promptTableHeaders = ["Start at second [0,1,...]", "Prompt"]
+
+default_prompt = """
+{
+ "prePrompt": "Huge spectacular Waterfall in ",
+ "prompts": {
+ "data": [
+ [0, "a dense tropical forest"],
+ [2, "a Lush jungle"],
+ [3, "a Thick rainforest"],
+ [5, "a Verdant canopy"]
+ ]
+ },
+ "postPrompt": "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),(tropical forest:1.4),(river:1.3) volumetric lighting ,epic, style by Alex Horley Wenjun Lin greg rutkowski Ruan Jia (Wayne Barlowe:1.2)",
+ "negPrompt": "frames, border, edges, borderline, text, character, duplicate, error, out of frame, watermark, low quality, ugly, deformed, blur, bad-artist"
+}
+"""
+
+empty_prompt = '{"prompts":{"data":[],"negPrompt":"", prePrompt:"", postPrompt:""}'
+
+invalid_prompt = {
+ "prompts": {
+ "data": [[0, "Your prompt-json is invalid, please check Settings"]],
+ },
+ "negPrompt": "Invalid prompt-json",
+ "prePromp": "Invalid prompt",
+ "postPrompt": "Invalid prompt",
+}
+
+available_samplers = [
+ s.name for s in modules.sd_samplers.samplers if "UniPc" not in s.name
+]
+
+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"
+)
diff --git a/iz_helpers/ui.py b/iz_helpers/ui.py
new file mode 100644
index 0000000..7f28b48
--- /dev/null
+++ b/iz_helpers/ui.py
@@ -0,0 +1,307 @@
+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,
+ available_samplers,
+ default_total_outpaints,
+ default_sampling_steps,
+ default_cfg_scale,
+ default_mask_blur,
+ default_sampler,
+)
+from .helpers import putPrompts, clearPrompts
+from .prompt_util import readJsonPrompt
+from .static_variables import promptTableHeaders
+
+
+def on_ui_tabs():
+ with gr.Blocks(analytics_enabled=False) as infinite_zoom_interface:
+ gr.HTML(
+ """
+
+ 
+ 
+
+
+ """
+ )
+ 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"):
+ with gr.Row():
+ batchcount_slider = gr.Slider(
+ minimum=1,
+ maximum=25,
+ value=shared.opts.data.get("infzoom_batchcount", 1),
+ step=1,
+ label="Batch Count",
+ )
+ main_outpaint_steps = gr.Number(
+ label="Total video length [s]",
+ value=default_total_outpaints,
+ precision=0,
+ interactive=True,
+ )
+
+ # safe reading json prompt
+ pr = shared.opts.data.get("infzoom_defPrompt", default_prompt)
+ jpr = readJsonPrompt(pr, True)
+
+ main_common_prompt_pre = gr.Textbox(
+ value=jpr["prePrompt"], label="Common Prompt Prefix"
+ )
+
+ main_prompts = gr.Dataframe(
+ type="array",
+ headers=promptTableHeaders,
+ datatype=["number", "str"],
+ row_count=1,
+ col_count=(2, "fixed"),
+ value=jpr["prompts"],
+ wrap=True,
+ )
+
+ main_common_prompt_suf = gr.Textbox(
+ value=jpr["postPrompt"], label="Common Prompt Suffix"
+ )
+
+ main_negative_prompt = gr.Textbox(
+ value=jpr["negPrompt"], label="Negative Prompt"
+ )
+
+ # these button will be moved using JS under 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_common_prompt_pre,
+ main_prompts,
+ main_common_prompt_suf,
+ main_negative_prompt,
+ ],
+ outputs=None,
+ )
+ importPrompts_button.upload(
+ fn=putPrompts,
+ outputs=[
+ main_common_prompt_pre,
+ main_prompts,
+ main_common_prompt_suf,
+ 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,
+ main_common_prompt_pre,
+ main_common_prompt_suf,
+ ],
+ )
+
+ with gr.Accordion("Render settings"):
+ with gr.Row():
+ seed = gr.Number(
+ label="Seed", value=-1, precision=0, interactive=True
+ )
+ main_sampler = gr.Dropdown(
+ label="Sampler",
+ choices=available_samplers,
+ value=default_sampler,
+ 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=default_cfg_scale,
+ label="Guidance Scale",
+ )
+ sampling_step = gr.Slider(
+ minimum=1,
+ maximum=150,
+ step=1,
+ value=default_sampling_steps,
+ 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", visible=False
+ )
+ 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_mask_blur = gr.Slider(
+ label="Mask Blur",
+ minimum=0,
+ maximum=64,
+ value=default_mask_blur,
+ )
+ inpainting_fill_mode = gr.Radio(
+ label="Masked content",
+ choices=["fill", "original", "latent noise", "latent nothing"],
+ value="latent noise",
+ type="index",
+ )
+
+ with gr.Tab("Post proccess"):
+ upscale_do = gr.Checkbox(False, label="Enable Upscale")
+ upscaler_name = gr.Dropdown(
+ label="Upscaler",
+ elem_id="infZ_upscaler",
+ 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,
+ step=0.5,
+ value=2,
+ )
+ 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-ERSGAn4x 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_common_prompt_pre,
+ main_prompts,
+ main_common_prompt_suf,
+ 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_mask_blur,
+ inpainting_fill_mode,
+ video_zoom_speed,
+ seed,
+ main_width,
+ main_height,
+ batchcount_slider,
+ main_sampler,
+ upscale_do,
+ upscaler_name,
+ upscale_by,
+ ],
+ outputs=[output_video, out_image, generation_info, html_info, html_log],
+ )
+
+ main_prompts.change(
+ fn=checkPrompts, inputs=[main_prompts], outputs=[generate_btn]
+ )
+
+ interrupt.click(fn=shared.state.interrupt(), inputs=[], outputs=[])
+ infinite_zoom_interface.queue()
+ return [(infinite_zoom_interface, "Infinite Zoom", "iz_interface")]
+
+
+def checkPrompts(p):
+ return gr.Button.update(
+ interactive=any(0 in sublist for sublist in p)
+ or any("0" in sublist for sublist in p)
+ )
diff --git a/iz_helpers/video.py b/iz_helpers/video.py
index c3d61a3..cb1c5d9 100644
--- a/iz_helpers/video.py
+++ b/iz_helpers/video.py
@@ -13,9 +13,8 @@ def write_video(file_path, frames, fps, reversed=True, start_frame_dupe_amount=1
if reversed == True:
frames = frames[::-1]
- # Get dimensions of the first frames, all subsequent has to be same sized
- for k in frames:
- assert (k.size == frames[0].size,"Different frame sizes found!")
+ # Drop missformed frames
+ frames = [frame for frame in frames if frame.size == frames[0].size]
# Create an imageio video writer, avoid block size of 512.
writer = imageio.get_writer(file_path, fps=fps, macro_block_size=None)
diff --git a/javascript/infinite-zoom-hints.js b/javascript/infinite-zoom-hints.js
new file mode 100644
index 0000000..e046f65
--- /dev/null
+++ b/javascript/infinite-zoom-hints.js
@@ -0,0 +1,49 @@
+// mouseover tooltips for various UI elements
+
+infzoom_titles = {
+ "Batch Count":"How many separate videos to create",
+ "Total video length [s]":"For each seconds frame (FPS) will be generated. Define prompts at which time they should start wihtin this duration.",
+ "Common Prompt Prefix":"Prompt inserted before each step",
+ "Common Prompt Suffix":"Prompt inserted after each step",
+ "Negative Prompt":"What your model shall avoid",
+ "Export prompts": "Downloads a JSON file to save all prompts",
+ "Import prompts": "Restore Prompts table from a specific JSON file",
+ "Clear prompts": "Start over, remove all entries from prompt table, prefix, suffix, negative",
+ "Custom initial image":"An image at the end resp. begin of your movie, depending or ZoomIn or Out",
+ "Custom exit image":"An image at the end resp. begin of your movie, depending or ZoomIn or Out",
+ "Zoom Speed":"Varies additional frames per second",
+ "Start at second [0,1,...]": "At which time the prompt has to be occure. We need at least one prompt starting at time 0",
+ "Generate video": "Start rendering. If it´s disabled the prompt table is invalid, check we have a start prompt at time 0"
+}
+
+
+onUiUpdate(function(){
+ gradioApp().querySelectorAll('span, button, select, p').forEach(function(span){
+ tooltip = infzoom_titles[span.textContent];
+
+ if(!tooltip){
+ tooltip = infzoom_titles[span.value];
+ }
+
+ if(!tooltip){
+ for (const c of span.classList) {
+ if (c in infzoom_titles) {
+ tooltip = infzoom_titles[c];
+ break;
+ }
+ }
+ }
+
+ if(tooltip){
+ span.title = tooltip;
+ }
+ })
+
+ gradioApp().querySelectorAll('select').forEach(function(select){
+ if (select.onchange != null) return;
+
+ select.onchange = function(){
+ select.title = infzoom_titles[select.value] || "";
+ }
+ })
+})
diff --git a/javascript/infinite-zoom.js b/javascript/infinite-zoom.js
index 8f7d546..5709977 100644
--- a/javascript/infinite-zoom.js
+++ b/javascript/infinite-zoom.js
@@ -1,9 +1,9 @@
// Function to download data to a file
-function exportPrompts(p, np, filename = "infinite-zoom-prompts.json") {
+function exportPrompts(cppre,p, cpsuf,np, filename = "infinite-zoom-prompts.json") {
- let J = { prompts: p, negPrompt: np }
+ let J = { prompts: p, negPrompt: np, prePrompt: cppre, postPrompt: cpsuf }
- var file = new Blob([JSON.stringify(J)], { type: "text/csv" });
+ var file = new Blob([JSON.stringify(J,null,2)], { type: "text/csv" });
if (window.navigator.msSaveOrOpenBlob) // IE10+
window.navigator.msSaveOrOpenBlob(file, filename);
else { // Others
diff --git a/scripts/infinite-zoom.py b/scripts/infinite-zoom.py
index a8238d7..60751b0 100644
--- a/scripts/infinite-zoom.py
+++ b/scripts/infinite-zoom.py
@@ -1,880 +1,5 @@
-import sys
-import os
-import time
-import json
-from jsonschema import validate
-
-import numpy as np
-import gradio as gr
-from PIL import Image
-import math
-import json
-
-from iz_helpers import shrink_and_paste_on_blank, write_video
-from webui import wrap_gradio_gpu_call
-from modules import script_callbacks, scripts
-import modules.shared as shared
-from modules.processing import (
- process_images,
- StableDiffusionProcessingTxt2Img,
- StableDiffusionProcessingImg2Img,
-)
-
-from scripts import postprocessing_upscale
-
-from modules.ui import create_output_panel, plaintext_to_html
-import modules.sd_models
-import modules.sd_samplers
-
-from modules import scripts
-
-usefulDirs = scripts.basedir().split(os.sep)[
- -2:
-] # contains install and our extension foldername
-jsonprompt_schemafile = (
- usefulDirs[0] + "/" + usefulDirs[1] + "/scripts/promptschema.json"
-)
-
-available_samplers = [s.name for s in modules.sd_samplers.samplers if "UniPc" not in s.name]
-
-default_prompt = """
-{
- "prompts":{
- "headers":["outpaint steps","prompt"],
- "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) "]
- ]
- },
- "negPrompt":"frames, borderline, text, character, duplicate, error, out of frame, watermark, low quality, ugly, deformed, blur bad-artist"
-}
-"""
-
-empty_prompt = (
- '{"prompts":{"data":[],"headers":["outpaint steps","prompt"]},"negPrompt":""}'
-)
-
-# must be python dict
-invalid_prompt = {
- "prompts": {
- "data": [[0, "Your prompt-json is invalid, please check Settings"]],
- "headers": ["outpaint steps", "prompt"],
- },
- "negPrompt": "Invalid prompt-json",
-}
-
-
-def closest_upper_divisible_by_eight(num):
- if num % 8 == 0:
- return num
- else:
- return math.ceil(num / 8) * 8
-
-
-# example fail: 720 px width * 1.66 upscale => 1195.2 => 1195 crash
-# 512 px * 1.66 = 513.66 = ?
-# assume ffmpeg will CUT to integer
-# 721 /720
-
-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 renderTxt2Img(prompt, negative_prompt, sampler, steps, cfg_scale, 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=-1,
- sampler_name=sampler,
- n_iter=1,
- steps=steps,
- cfg_scale=cfg_scale,
- width=width,
- height=height,
- )
- processed = process_images(p)
- return processed
-
-
-def renderImg2Img(
- prompt,
- negative_prompt,
- sampler,
- steps,
- cfg_scale,
- 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=-1,
- 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)
- return processed
-
-
-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 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 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,
- outputsizeW,
- outputsizeH,
- batchcount,
- sampler,
- upscale_do,
- upscaler_name,
- upscale_by,
- 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,
- outputsizeW,
- outputsizeH,
- sampler,
- upscale_do,
- upscaler_name,
- upscale_by,
- 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,
- outputsizeW,
- outputsizeH,
- sampler,
- upscale_do,
- upscaler_name,
- upscale_by,
- 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 = {}
- for x in prompts_array:
- try:
- key = int(x[0])
- value = str(x[1])
- prompts[key] = value
- except ValueError:
- pass
- assert len(prompts_array) > 0, "prompts is empty"
-
- 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")
-
- if custom_init_image:
- current_image = custom_init_image.resize(
- (width, height), resample=Image.LANCZOS
- )
- else:
- load_model_from_setting("infzoom_txt2img_model", progress, "Loading Model for txt2img: ")
-
- processed = renderTxt2Img(
- prompts[min(k for k in prompts.keys() if k >= 0)],
- negative_prompt,
- sampler,
- num_inference_steps,
- guidance_scale,
- width,
- height,
- )
- current_image = processed.images[0]
-
- 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: " )
-
- for i in range(num_outpainting_steps):
- print_out = "Outpaint step: " + str(i + 1) + " / " + str(num_outpainting_steps)
- print(print_out)
- if progress:
- progress(((i + 1) / num_outpainting_steps), desc=print_out)
-
- 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")
-
- processed = renderImg2Img(
- prompts[max(k for k in prompts.keys() if k <= i)],
- negative_prompt,
- sampler,
- num_inference_steps,
- guidance_scale,
- 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]
-
- current_image.paste(prev_image, mask=prev_image)
-
- # 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
- )
-
- prev_image_fix_crop = shrink_and_paste_on_blank(
- prev_image_fix, interpol_width2, interpol_height2
- )
-
- interpol_image.paste(prev_image_fix_crop, mask=prev_image_fix_crop)
-
- if upscale_do and progress:
- progress(((i + 1) / num_outpainting_steps), desc="upscaling interpol")
-
- all_frames.append(
- do_upscaleImg(interpol_image, upscale_do, upscaler_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
- )
-
- 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)
- 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(""),
- )
-
-
-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(""),
- ]
-
-
-def on_ui_tabs():
- with gr.Blocks(analytics_enabled=False) as infinite_zoom_interface:
- gr.HTML(
- """
-
-
-
-
-
- """
- )
- 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=2,
- 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"],
- datatype=["number", "str"],
- row_count=1,
- col_count=(2, "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],
- )
-
- 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", visible=False
- ) # TODO: implement exit-image rendering
-
- batchcount_slider = gr.Slider(
- minimum=1,
- maximum=25,
- value=shared.opts.data.get("infzoom_batchcount", 1),
- step=1,
- label="Batch Count",
- )
- 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")
- upscaler_name = gr.Dropdown(
- label="Upscaler",
- elem_id="infZ_upscaler",
- 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-ERSGAn4x 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,
- main_width,
- main_height,
- batchcount_slider,
- main_sampler,
- upscale_do,
- upscaler_name,
- upscale_by,
- ],
- 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")]
-
-
-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,
- ),
- )
-
-
+from modules import script_callbacks
+from iz_helpers.ui import on_ui_tabs
+from iz_helpers.settings import on_ui_settings
script_callbacks.on_ui_tabs(on_ui_tabs)
-script_callbacks.on_ui_settings(on_ui_settings)
+script_callbacks.on_ui_settings(on_ui_settings)
\ No newline at end of file
diff --git a/scripts/promptschema.json b/scripts/promptschema.json
deleted file mode 100644
index b7fcfd4..0000000
--- a/scripts/promptschema.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
- "$schema": "http://json-schema.org/draft-07/schema#",
- "type": "object",
- "properties": {
- "prompts": {
- "type": "object",
- "properties": {
- "data": {
- "type": "array",
- "items": {
- "type": "array",
- "items": [
- {
- "oneOf": [
- {
- "type": "integer",
- "minimum": 0
- },
- {
- "type": "string"
- }
- ]
- },
- {
- "type": "string"
- }
- ],
- "minItems": 0,
- "maxItems": 999,
- "uniqueItems": false
- },
- "minItems": 0
- },
- "headers": {
- "type": "array",
- "items": {
- "type": "string"
- },
- "minItems": 2
- }
- },
- "required": ["data", "headers"]
- },
- "negPrompt": {
- "type": "string"
- }
- },
- "required": ["prompts", "negPrompt"]
- }
\ No newline at end of file