Quick Guide to Deforum v05

Art by: neuro @ https://twitter.com/neurodiculous

This quick user guide is intended as a LITE reference for different aspects and items found within the Deforum notebook. It is intended for version 05, which was release 10/2//2022

While this reference guide includes different explanations of parameters, it is not to be used as a complete troubleshooting resource. The user is encouraged to explore and create their own style, using this guide as a compass to help better their inspiration. The best way to make this guide effective is to share your findings and experiences with the community! -ScottieFox

The AI art scene is evolving rapidly. Take this guide lightly. Methods, models, and notebooks will change. All the info in this guide will become irrelevant. Sad but true :’( -huemin

Table of Contents 2

Stability.AI Model Terms of Use 2

Change Log 3

Model Download (Automatic) 4

Model Download (Manual) 4

Notebook Overview 5

Stability.AI Model Terms of Use

By using this Notebook, you agree to the following Terms of Use, and license:

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.

The CreativeML OpenRAIL License specifies:

You can't use the model to deliberately produce nor share illegal or harmful outputs or content

CompVis claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license

You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)

Please read the full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license

Change Log

## What's Changed

* Print some useful anim_args by @johnnypeck in https://github.com/deforum/stable-diffusion/pull/63

* Update: cv2-based frame unpacking (vid2frames) by @Bardia323 in https://github.com/deforum/stable-diffusion/pull/66

* Add perspective flipping to 2D animation mode by @kabachuha in https://github.com/deforum/stable-diffusion/pull/64

* Add custom settings import from file by @kabachuha in https://github.com/deforum/stable-diffusion/pull/65

* Add schedule parameters evaluation as math expressions by @kabachuha in https://github.com/deforum/stable-diffusion/pull/72

* Printing/saving of intermediate steps by @enzymezoo-code in https://github.com/deforum/stable-diffusion/pull/73

* Video init masking by @enzymezoo-code in https://github.com/deforum/stable-diffusion/pull/73

* Improved masking by @enzymezoo-code in https://github.com/deforum/stable-diffusion/pull/74

* Weighted prompts by @kabachuha in https://github.com/deforum/stable-diffusion/pull/78

* Auto-download models and added robo-diffusion by @nousr in https://github.com/deforum/stable-diffusion/pull/83

* Add waifu v3 by @deforum in https://github.com/deforum/stable-diffusion/pull/88

## New Contributors

* @johnnypeck made their first contribution in https://github.com/deforum/stable-diffusion/pull/63

* @Bardia323 made their first contribution in https://github.com/deforum/stable-diffusion/pull/66

* @kabachuha made their first contribution in https://github.com/deforum/stable-diffusion/pull/64

* @nicolai256 made their first contribution in https://github.com/deforum/stable-diffusion/pull/69

* @nousr made their first contribution in https://github.com/deforum/stable-diffusion/pull/83

**Full Changelog**: https://github.com/deforum/stable-diffusion/compare/v0.4.0...v0.5.0

Model Download (Automatic)

In Deforum an automatic model download feature has been added - you no longer need to download model’s manually and place them in the correct folder. All model weights, when selected, are downloaded from huggingface and placed in the appropriate model folder.

To download official model weights within Deforum you will need to have an account on huggingface and provide your username and an access token within the notebook.

You can make an access token by going to your profile > settings > access tokens > new token

Provide your username and access token when prompted in Deforum. Afterwards, the notebook will attempt to download the model. If you run into errors automatically downloading models, please try again, sometime the colab session times out.

Deforum v05 has the following models configured for automatic download:

Official Stable Diffusion Weights (requires huggingface login and token)

Stable Diffusion v1.4
Stable Diffusion v1.3
Stable Diffusion v1.2
Stable Diffusion v1.1

Unofficial Nousr Robo Diffusion

robo-diffusion-v1.ckpt

Unofficial Waifu Diffusion v3

model-epoch05-float16.ckpt

Model Download (Manual)

Make an account on huggingface, download the .ckpt file, and place the file in Google Drive.

The Deforum Stable Diffusion notebook requires the user to download model weights (~4GB) and correctly link the model weights to the Colab Notebook. The following steps will walk you through downloading model weights and uploading them to google drive:

Go to https://huggingface.co and sign up to create an account

Once signed into your account, navigate to https://huggingface.co/CompVis. Here you will see all the checkpoints available for download marked with “-original”.

Select an “-original” model from the “CompVis” library (stable-diffusion-v-1-4-original) and download the weights. You will need to accept the terms of use. At the time of this writing sd-v1-4.ckpt is the best model.

While you are waiting for the model to download to your computer, open the Deforum Notebook and run the “Model and Output Paths” cell by clicking the play button. Running this cell will configure your Google Drive with the correct folder and file structure. Alternatively, you can create the following folders on your google drive:

Once the download is complete you will need to upload the model weights to this models folder.

Ready to go!

Notebook Overview

https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb

1. SETUP

NVIDIA GPU:

code, when run, will display info about the GPU that was assigned.

This cell will give you information regarding the gpu you have connected to in the run session. Diffusion in general makes heavy use of VRAM (video RAM) to render images. Colab GPU tier list from best to worst: A100 (40GB VRAM), V100 (16GB VRAM), P100 (16GB VRAM), T4, K80.

Model and Output Paths:

models_path: -looks in runtime for uploaded model
output_path: -directs images/file to a place in the runtime

Google Drive Path Variables (Optional):

mount_google_drive , when selected will redirect paths to drive instead of runtime
models_path_gdrive , location of model on Google Drive
(default /content/drive/MyDrive/AI/models)
output_path_gdrive , location of images/file to be output in Google Drive

The notebook expects the following path variables to be defined: models_path and output_path. These locations will be used to access the Stable Diffusion .pth model weights and save the diffusion output renders, respectively. There is the option to use paths locally or on Google Drive. If you desire to use paths on Google drive, mount_google_drive must be True. Mounting Gdrive will prompt you to access your Drive, to read/write/save images.

Setup Environment:

setup_enviroment , when checked will build environment to handle pip/installs
print_subprocess, choose to show items being pulled and built

Running this cell will download github repositories, import python libraries, and create the necessary folders and files to configure the Stable Diffusion model. Sometimes there may be issues where the Setup Environment cells do not load properly and you will encounter errors when you start the run. Verify the Setup Environment cells have been run without any errors.

Python Definitions:

pulls/pips/installs functions and definitions into built environment for later use during a run
defines variables from libraries and loads them to runtime

Running this cell will define the required functions to proceed with making images. Verify the Python Definitions cell has been run without any errors.

Select and Load Model:

model_config ,: type of instruction file: default .yaml, or custom option
model_checkpoint , the dataset to auto downloaded
custom_config_path, blank unless intending to use a custom .yaml file
custom_checkpoint_path, blank unless using a .cpkt file not listed
load_on_run_all, when checked will be an include cell for RUN ALL function
check_sha256, will perform comparison against checksum (check hash for file integrity)
map_location, utilizes CUDA cores on GPU[default], or uses CPU[slow] (not recommended)

In order to load the Stable Diffusion model, Colab needs to know where to find the model_config file and the model_checkpoint. The model_config file contains information about the model architecture. The model_checkpoint contains model weights which correspond to the model architecture. For troubleshooting verify that both the config and weight path variables are correct. By default the notebook expects the model config and weights to be located in the model_path. You can provide custom model weights and config paths by selecting “custom” in both the model_config and model_checkpoint dropdowns. Sometimes there are issues with downloading the model weights and the file is corrupt. The check_sha256 function will verify the integrity of the model weights and let you know if they are okay to use. The map_location allows the user to specify where to load model weights. For most colab users, the default “GPU” map location is best.

settings on next page →

2. SETTINGS

2a. Animation Settings

Animation modes:

NONE, When selected, will ignore all functions in animation mode and will output batches of images coherently unrelated to each other, as specified by the prompts list. The prompts used will follow the non-scheduled, non-animation list. The number of images that are to be produced is defined in a later cell under “n_batches”.
2D: When selected will ignore the “none mode” prompts and refer to the prompts that are scheduled with a frame number before them. 2D mode will attempt to string the images produced in a sequence of coherent outputs. The number of output images to be created is defined by “max_frames”. The motion operators that control 2D mode are as follows:
“Border, angle, zoom, translation_x, translation_y, noise_schedule, contrast_schedule, color_coherence, diffusion_cadence, and save depth maps”. Other animation parameters have no effect during 2D mode. Resume_from_timestring is available during 2D mode. (more details below)

3D, When selected will ignore the “none mode” prompts and refer to the prompts that are scheduled with a frame number before them. 3D mode will attempt to string the images produced in a sequence of coherent outputs. The number of output images to be created is defined by “max_frames”. The motion operators that control 3D mode are as follows:

“Border, translation_x, translation_y, rotation_3d_x, rotation_3d_y, rotation_3d_z, noise_schedule, contrast_schedule, color_coherence, diffusion_cadence, 3D depth warping, midas_weight, fov, padding_mode, sampling_mode, and save_depth_map. Resume_from_timestring is available during 3D mode. (more details below)

video_input, When selected, will ignore all motion parameters and attempt to reference a video loaded into the runtime, specified by the video_init_path. Video Input mode will ignore the “none mode” prompts and refer to the prompts that are scheduled with a frame number before them. “Max_frames” is ignored during video_input mode, and instead, follows the number of frames pulled from the video’s length. The notebook will populate images from the video into the selected drive as a string of references to be impacted. The number of frames to be pulled from the video is based on “extract_nth_frame”. Default of 1 will extract every single frame of the video. A value of 2 will skip every other frame. Values of 3 and higher will effectively skip between those frames yielding a shorter batch of images. Currently, video_input mode will ignore all other coherence parameters, and only affect each frame uniquely. Resume_from_timestring is NOT available with Video_Input mode.

interpolation_mode, When selected, will ignore all other motion and coherence parameters, and attempt to blend output frames between animation prompts listed with a schedule frame number before them. If interpolate_key_frame mode is checked, the number of output frames will follow your prompt schedule. If unselected, the interpolation mode will follow an even schedule of frames as specified by “interpolate_x_frames”, regardless of prompt numbering. A default value of 4 will yield four frames of interpolation between prompts.

Animation Parameters:

animation_mode, selects type of animation (see above)
max_frames, specifies the number of 2D or 3D images to output
border, controls handling method of pixels to be generated when the image is smaller than the frame. “Wrap” pulls pixels from the opposite edge of the image, while “Replicate” repeats the edge of the pixels, and extends them. Animations with quick motion may yield “lines” where this border function was attempting to populate pixels into the empty space created.

Motion Parameters:

motion parameters are instructions to move the canvas in units per frame

angle, 2D operator to rotate canvas clockwise/anticlockwise in degrees per frame
zoom, 2D operator that scales the canvas size, multiplicatively [static = 1.0]
translation_x, 2D & 3D operator to move canvas left/right in pixels per frame
translation_y, 2D & 3D operator to move canvas up/down in pixels per frame
translation_z, 3D operator to move canvas towards/away from view [speed set by FOV]
rotation_x, 3D operator to tilt canvas up/down in degrees per frame
rotation_y, 3D operator to pan canvas left/right in degrees per frame
rotation_z, 3D operator to roll canvas clockwise/anticlockwise
flip_2D_perspective, enables 2D mode functions to simulate “faux” 3D movement
perspective_flip_theta, the “roll” effect angle
perspective_flip_phi, the “tilt” effect angle
perspective_flip_gamma, the “pan” effect angle
perspective_flip_fv, the 2D vanishing point of perspective (rec’d range 30-160)
noise_schedule, amount of graininess to add per frame for diffusion diversity
strength_schedule, amount of presence of previous frame to influence next frame, also controls steps in the following formula [steps - (strength_schedule * steps)] (more details under: “steps”)
contrast_schedule, adjusts the overall contrast per frame [default neutral at 1.0]

Coherence:

color_coherence, select between NONE, LAB, HSV, RGB

LAB: Perceptual Lightness* A * B axis color balance (search “cielab”)
HSV: Hue Saturation & Value color balance.
RGB: Red Green & Blue color balance.

The color coherence will attempt to sample the overall pixel color information, and trend those values analyzed in the 0th frame, to be applied to future frames. LAB is a more linear approach to mimic human perception of color space - a good default setting for most users.

HSV is a good method for balancing presence of vibrant colors, but may produce unrealistic results - (ie.blue apples) RGB is good for enforcing unbiased amounts of color in each red, green and blue channel - some images may yield colorized artifacts if sampling is too low.

diffusion_cadence, controls the frequency of frames to be affected by diffusion [1-8]

The diffusion cadence will attempt to follow the 2D or 3D schedule of movement as per specified in the motion parameters, while enforcing diffusion on the frames specified. The default setting of 1 will cause every frame to receive diffusion in the sequence of image outputs. A setting of 2 will only diffuse on every other frame, yet motion will still be in effect. The output of images during the cadence sequence will be automatically blended, additively and saved to the specified drive. This may improve the illusion of coherence in some workflows as the content and context of an image will not change or diffuse during frames that were skipped. Higher values of 4-8 cadence will skip over a larger amount of frames and only diffuse the “Nth” frame as set by the diffusion_cadence value. This may produce more continuity in an animation, at the cost of little opportunity to add more diffused content. In extreme examples, motion within a frame will fail to produce diverse prompt context, and the space will be filled with lines or approximations of content - resulting in unexpected animation patterns and artifacts. Video Input & Interpolation modes are not affected by diffusion_cadence.

3D Depth Warping:

use_depth_warping, enables instructions to warp an image dynamically in 3D mode only.
midas_weight, sets a midpoint at which a depthmap is to be drawn: range [-1 to +1]
fov, adjusts the scale at which a canvas is moved in 3D by the translation_z value

FOV (field of view/vision) in deforum, will give specific instructions as to how the translation_z value affects the canvas. Range is -180 to +180. The value follows the inverse square law of a curve in such a way that 0 FOV is undefined and will produce a blank image output. A FOV of 180 will flatten and place the canvas plane in line with the view, causing no motion in the Z direction. Negative values of FOV will cause the translation_z instructions to invert, moving in an opposite direction to the Z plane, while retaining other normal functions.A value of 30 fov is default whereas a value of 100 would cause transition in the Z direction to be more smooth and slow. Each type of art and context will benefit differently from different FOV values. (ex. “Still-life photo of an apple” will react differently than “A large room with plants”)

FOV also lends instruction as to how a midas depth map is interpreted. The depth map (a greyscale image) will have its range of pixel values stretched or compressed in accordance with the FOV in such a fashion that the illusion of 3D is more pronounced at lower FOV values, and more shallow at values closer to 180. At full FOV of 180, no depth is perceived, as the midas depth map has been compressed to a single value range.

padding_mode, instructs the handling of pixels outside the field of view as they come into the scene. ‘Border” will attempt to use the edges of the canvas as the pixels to be drawn. “Reflection” will attempt to approximate the image and tile/repeat pixels, whereas “Zeros” will not add any new pixel information.
sampling_mode, choose from Bicubis, Bilinear or Nearest modes.

In image processing, bicubic interpolation is often chosen over bilinear or nearest-neighbor interpolation in image resampling, when speed is not an issue. In contrast to bilinear interpolation, which only takes 4 pixels (2×2) into account, bicubic interpolation considers 16 pixels (4×4). Images resampled with bicubic interpolation are smoother and have fewer interpolation artifacts.

save_depth_map, will output a greyscale depth map image alongside the output images.

Video Input:

video_init_path, the directory at which your video file is located for Video INput mode only.
extract_nth_frame, during the run sequence, only frames specified by this value will be extracted, saved, and diffused upon. A value of 1 indicates that every frame is to be accounted for. Values of 2 will use every other frame for the sequence. Higher values will skip that number of frames respectively.
overwrite_extracted_frames, when enabled, will re-extract video frames each run.

When using video_input mode, the run will be instructed to write video frames to the drive. If you’ve already populated the frames needed, uncheck this box to skip past redundant extraction, and immediately start the render. If you have not extracted frames, you must run at least once with this box checked to write the necessary frames.

use_video_mask, video_input mode only, enables the extraction and use of a separate video file intended for use as a mask. White areas of the extracted video frames will not be affected by diffusion, while black areas will be fully effected. Lighter/darker areas are affected dynamically.
video_mask_path, the directory in which your mask video is located.

Interpolation:

interpolate_key_frames, selects whether to ignore prompt schedule or _x_frames.
interpolate_x_frames, the number of frames to transition thru between prompts (when interpolate_key_frames = true, then the numbers in front of the animation prompts will dynamically guide the images based on their value. If set to false, will ignore the prompt numbers and force interpole_x_frames value regardless of prompt number)

Resume Animation:

resume_from_timestring, instructs the run to start from a specified point
resume_timestring, the required timestamp to reference when resuming

Currently only available in 2D & 3D mode, the timestamp is saved as the settings .txt file name as well as images produced during your previous run. The format follows:

yyyymmddhhmmss - a timestamp of when the run was started to diffuse.

prompts on next page →

2b. PROMPTS

In the above example, we have two groupings of prompts: the still frames *prompts* on top, and the animation_prompts below. During the “NONE” animation mode, the diffusion will look to the top group of prompts to produce images. In all other modes, (2D, 3D etc) the diffusion will reference the second lower group of prompts.

Careful attention to the syntax of these prompts is critical to be able to run the diffusion.

For still frame image output, numbers are not to be placed in front of the prompt, since no “schedule” is expected during a batch of images. The above prompts will produce and display a forest image and a separate image of a woman, as the outputs.

During 2D//3D animation runs, the lower group with prompt numbering will be referenced as specified. In the example above, we start at frame 0: - an apple image is produced. As the frames progress, it remains with an apple output until frame 20 occurs, at which the diffusion will now be directed to start including a banana as the main subject, eventually replacing the now no longer referenced apple from previous.

Interpolation mode, however, will “tween” the prompts in such a way that firstly, 1 image each is produced from the list of prompts. An apple, banana, coconut, and a durian fruit will be drawn. Then the diffusion begins to draw frames that should exist between the prompts, making hybrids of apples and bananas - then proceeding to fill in the gap between bananas and coconuts, finally resolving and stopping on the last image of the durian, as its destination. (remember that this exclusive mode ignores max_frames and draws the interpolate_key_frame/x_frame schedule instead.

Many resources exist for the context of what a prompt should include. It is up to YOU, the dreamer, to select items you feel belong in your art. Currently, prompts weights are not implemented yet in deforum, however following a template should yield fair results:

[Medium] [Subject] [Artist] [Details] [Repository]

Ex. “A Sculpture of a Purple Fox by Alex Grey, with tiny ornaments, popular on CGSociety”,

run on next page →

3. Run

Load Settings:

override_settings_with_file, when checked ,ignores all settings and refers to a .txt file
custom_settings_file, location of settings file to be used for override instructions

Image settings:

W, defines the output width of the final image in pixels
H, defines the output height of the final image in pixels

Dimensions in output must be multiples of 64 pixels otherwise, the resolution will be rounded down to the nearest compatible value. Proper values 128, 192, 256, 320, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024. Values above these recommended settings are possible, yet may yield OOM (out of memory) issues, as well as improper midas calculations. The model was trained on a 512x512 dataset, and therefore must extend its diffusion outside of this “footprint” to cover the canvas size. A wide landscape image may produce 2 trees side-by-side as a result, or perhaps 2 moons on either side of the sky. A tall portrait image may produce faces that are stacked instead of centered.

Sampling Settings:

seed, a starting point for a specific deterministic outcome, (-1 = random starting point)

Stable Diffusion outputs are deterministic, meaning you can recreate images using the exact same settings and seed number. Choosing a seed number of -1 tells the code to pick a random number to use as the seed. When a random seed is chosen, it is printed to the notebook and saved in the image settings .txt file.

sampler, method in which the image is encoded and decoded from latent space

klms = Kernel Least Mean Square
dpm2 = Denoise Probabilistic Model
dpm2_Ancestral = dpm2 with reverse sampling path
heun = founded off of Euler by Karl Heun (maths & derivative solving)
euler = fractional-order anisotropic denoise (Euler-Lagrange equations)
euler_ancestral = reverse sampling path to Euler
plms = Pre-trained Language Model(s)
ddim = Denoising Diffusion Probabilistic Models

steps, the number of iterations intended for a model to reach its prompt

Considering that during one frame, a model will attempt to reach its prompt by the final step in that frame. By adding more steps, the frame is sliced into smaller increments as the model approaches completion. Higher steps will add more defining features to an output at the cost of time. Lower values will cause the model to rush towards its goal, providing vague attempts at your prompt. Beyond a certain value, if the model has achieved its prompt, further steps will have very little impact on final output, yet time will still be a wasted resource. Some prompts also require fewer steps to achieve a desirable acceptable output.

During 2D & 3D animation modes, coherence is important to produce continuity of motion during video playback. The value under Motion Parameters, “strength_schedule” achieves this coherence by utilizing a proportion of the previous frame, into the current diffusion. This proportion is a scale of 0 - 1.0 , with 0 meaning there’s no cohesion whatsoever, and a brand new unrelated image will be diffused. A value of 1.0 means ALL of the previous frame will be utilized for the next, and no diffusion is needed. Since this relationship of previous frame to new diffusion consists of steps diffused previously, a formula was created to compensate for the remaining steps to justify the difference. That formula is as such:
Target Steps - (strength_schedule * Target Steps)

Your first frame will, however, yield all of the steps - as the formula will be in effect afterwards.

scale, a measurement of how much enforcement to apply to an overall prompt.

A normal range of 7-10 is appropriate for most scenes, however some styles and art will require more extreme values. At scale values below 3, the model will loosely impose a prompt with many areas skipped and left uninteresting or simply grayed-out. Values higher than 25 may over enforce a prompt causing extreme colors of over saturation, artifacts and unbalanced details. For some use-cases this might be a desirable effect. During some animation modes, having a scale that is too high, may trend color into a direction that causes bias and overexposed output.

ddim_eta, ONLY enabled in ddim sampler mode, will control a ratio of ddim to ddpm sampling methods, with a range of -1 to +1 with 0 being less randomized determinism.

Save & Display Settings:

save_samples, will save output images to the specified drive, including cadence frames
save_settings, will save a snapshot .txt of all settings used to start a run with a timestamp
display samples, shows on-screen image of the completed output
save_sample_per_step, outputs all intermediate steps of a single frame (many files)
show_sample_per_step, displays all images of each step of the output

Prompt Settings:

prompt_weighting, enables interpretation of weight syntax in a prompt
normailze_prompt_weights, multiplies by a factor to have sum of all = 1.0
log_weighted_subprompts, displays tokenization of prompt context

Batch Settings:

n_batch, produces n amounts of outputs per prompt in ‘none’ animation mode
batch_name, will create a folder and save output content to that directory location
seed behavior, will perform progressive changes on the seed starting point based on settings:

Iter = incremental change (ex 77, 78, 79 ,80, 81, 82, 83…)

Fixed = no change in seed (ex 33, 33, 33, 33, 33, 33…)

Random = random seed (ex 472, 12, 927812, 8001, 724…)

Note: seed -1 will choose a random starting point, following the seed behavior thereafter

Troubleshoot: a “fixed” seed in 2D/3D mode will overbloom your output. Switch to “iter”

make_grid, will take take still frames and stitch them together in a preview grid
grid_rows, arrangement of images set by make_grid

Init_Settings:

use_init, uses a custom image as a starting point for diffusion
strength, determines the presence of an init_image/video on a scale of 0-1 with 0 being full diffusion, and 1 being full init source.

Note: even with use_init unchecked, video input is still affected.

init_image, location of an init_image to be used

Note: in ‘none’ animation mode, a folder of images may be referenced here.

use_mask, adds an image for instructions as to which part of an image to diffuse by greyscale
mask_file, location of the mask image to be used
invert_mask, ranges the greyscale of a mask from “0 to 1” into “1 to 0”
mask_brightness_adjust, changes the value floor of the mask, controlling diffusion overall
mask_constract_adjust, clamps min/max values of the mask to limit areas of diffusion. Note: lighter areas of the mask = no diffusion, darker areas enforce more diffusion

create video from frames on next page →

4. Create video from frames

skip_video_for_run_all, when running-all this notebook, video construction will be skipped until manually checked and the cell is re-run. It is off by default.
fps, framerate at which the video will be rendered
image_path, location of images intended to be stitched in sequence. The user must update this parameter to reflect the timestamp needed.
mp4_path, location to save the resulting video to
max_frames, the quantity of images to be prepared for stitching