RunwayML Gen 1 vs Automatic1111 - Video creation with StableDiffusion

Render Realm · Beginner ·🎨 Image & Video AI ·3y ago
In this video we take a deeper dive into creating videos with StableDiffusion, comparing RunwayML Gen 1 with Automatic1111. First we will create a short animation in Blender, then feed it first into RunwayML Gen1 and later into Automatic1111, Batch img2img / ControlNet and explain the whole workflow of creating a video animation in each system. We also will show, how to reduce flickering and temporal incoherences in StableDiffusion videos considerably. Finally, we will compare the results and talk about the pros and cons of each system, as well as the requirements, support and give a final conclusion. Chapters: 00:00 Introduction 01:16 Preparing some simple video footage in Blender 05:00 Creating a video animation with RunwayML Gen 1, using our video footage as an input 09:54 Creating a video animation with Automatic1111/batch img2img/controlnet , using the same footage 13:40 Improving the temporal coherence in Automatic1111 videos 14:42 Comparison, pros and cons of RunwayML Gen 1 vs Automatic1111, final conclusion Also visit our music channel to watch some great music-videos, created with StableDiffusion, Unreal Engine and Blender: https://www.youtube.com/@-vero- Useful Links: --------------------- RunwayML website: https://runwayml.com Local installation guide for Automatic1111 on a Windows-PC: https://stable-diffusion-art.com/install-windows/ and on a Mac with Apple Silicon: https://stable-diffusion-art.com/install-mac/ Running StableDiffusion Automatic1111 on Google Colab: https://stable-diffusion-art.com/automatic1111-colab/ Installing the ControlNet extension for Automatic1111: https://github.com/Mikubill/sd-webui-controlnet Link to the Mixamo site: https://www.mixamo.com/ Link to Sketchfab for downloading free 3d models, that you can use in Blender: https://sketchfab.com/ Download Blender: https://www.blender.org/download/ Creating Mixamo animations in Blender: https://youtu.be/eFjECaeY4Go Using LoRA models in StableDiffusion Automatic1111: ht
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

What makes an AI image workflow useful for real commercial output?
Learn how to create a useful AI image workflow for commercial output, focusing on repeatability, versatility, and clarity
Dev.to AI
How to Write Better AI Image Prompts for Midjourney (With Examples That Actually Work)
Learn to write effective AI image prompts for Midjourney with actionable examples and techniques
Medium · ChatGPT
Image to Video AI: The Complete Workflow Playbook That Actually Produces Results
Learn a step-by-step workflow for image-to-video AI that produces results, from preparation to delivery
Medium · AI
Image Harvest v1.0.2: Internationalization, Free Pro Trial & Quality-of-Life Improvements
Learn about Image Harvest v1.0.2, a Chrome extension with internationalization, free pro trial, and quality-of-life improvements, and how to utilize it for privacy-first image extraction
Dev.to · kyriewen

Chapters (6)

Introduction
1:16 Preparing some simple video footage in Blender
5:00 Creating a video animation with RunwayML Gen 1, using our video footage as an in
9:54 Creating a video animation with Automatic1111/batch img2img/controlnet , using t
13:40 Improving the temporal coherence in Automatic1111 videos
14:42 Comparison, pros and cons of RunwayML Gen 1 vs Automatic1111, final conclusion
Up next
Krea 2 makes Diffusion FUN Again!
MattVidPro
Watch →