Latent blending enables the creation of super-smooth video transitions between prompts. Powered by stable diffusion 2.1, this method involves specific mixing of intermediate latent representations to create a seamless transition – with users having the option to choose full customization or preset options.

Quickstart

fp_ckpt = 'path_to_SD2.ckpt'
fp_config = 'path_to_config.yaml'

sdh = StableDiffusionHolder(fp_ckpt, fp_config, 'cuda')
lb = LatentBlending(sdh)

lb.load_branching_profile(quality='medium', depth_strength=0.4)
lb.set_prompt1('photo of my first prompt1')
lb.set_prompt2('photo of my second prompt')

imgs_transition = lb.run_transition()

Gradio UI

To run the UI on your local machine, run gradio_ui.py

Example 1: Simple transition

To run a simple transition between two prompts, run example1_standard.py

Example 2: Inpainting transition

To run a transition between two prompts where you want some part of the image to remain static, run example2_inpaint.py

Example 3: Multi transition

To run multiple transition between K prompts, resulting in a stitched video, run example3_multitrans.py

Customization

Most relevant parameters

Change the height/width

lb.set_height(512)
lb.set_width(1024)

Change guidance scale

lb.set_guidance_scale(5.0)

depth_strength / list_injection_strength

The strength dictates how early the blending process starts. The closer its value is to zero, the more inventive the results will be; whereas, a value closer to one indicates a more simple alpha blending.

Set up the branching structure

There are three ways to change the branching structure.

Presets

quality = 'medium' #choose from lowest, low, medium, high, ultra
depth_strength = 0.5 # see above (Most relevant parameters)

lb.load_branching_profile(quality, depth_strength)

Autosetup tree setup

num_inference_steps = 30 # the number of diffusion steps
list_nmb_branches = [2, 4, 8, 20]
list_injection_strength = [0.0, 0.3, 0.5, 0.9]

lb.autosetup_branching(num_inference_steps, list_nmb_branches, list_injection_strength)

Fully manual

depth_strength = 0.5 # see above (Most relevant parameters)
num_inference_steps = 30 # the number of diffusion steps
nmb_branches_final = 20 # how many diffusion images will be generated for the transition

lb.setup_branching(depth_strength, num_inference_steps, nmb_branches_final)

Installation

Packages

pip install -r requirements.txt

Download Models from Huggingface

Download the Stable Diffusion v2-1_768 Model

Download the Stable Diffusion Inpainting Model

Download the Stable Diffusion x4 Upscaler

(Optional but recommended) Install Xformers

With xformers, stable diffusion will run faster with smaller memory inprint. Necessary for higher resolutions / upscaling model.

conda install xformers -c xformers/label/dev

Alternatively, you can build it from source:

# (Optional) Makes the build much faster
pip install ninja
# Set TORCH_CUDA_ARCH_LIST if running and building on different GPU types
pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
# (this can take dozens of minutes)

How does it work

what makes a transition a good transition?

• absence of movement
• every frame looks like a credible photo