Using AI to generate consistent characters and locations (from different angles) is still a challenge, although models continue to improve. A few recent examples of successes and failures. Consistent Characters I typically start from a head/face, then expand to a full body. But generating the same character from multiple angles (front, rear, side, etc) has … More Consistent Characters, Consistent Locations
The Big Red Stripe channel on YouTube has come great videos for filmmakers. I was watching The EXACT System Pros Use to Revise Their Screenplays where he goes through steps a professional screenplay writer may follow. My personal current interest is in writing scripts for episodes to produce using AI video generation (using ComfyUI in … More The Pro Formula – have a repeatable method
I am interested in ComfyUI for creating films where you have a scene with multiple shots at the same location, from different angles. An example can be seen in one of Mick’s videos where he improves the reliability of the background using a 360 location image. He uses Olm DragCrop to select a rectangular portion … More ComfyUI and Cropping from 360 Images
I want to create a short series on YouTube, using AI generated video. I posted previously about my planned pipeline. As I have learnt more some aspects have become clearer. This post updates some of those details. Buy a Bigger Disk I have a new desktop with a 4TB D: drive. I just filled it. … More AI Movie Pipeline Updates
If you have been following this series of posts, you will know I am learning how to create a LoRA character model for consistent character rendering with Wan2.1 in ComfyUI. There are lots of videos and posts, but they frequently have problems when I try them. So here I start with generating faces until I … More ComfyUI and Wan 2.1 Head to Fully Body Images
I have been writing a series of blog posts on my journey to create an AI generated series on YouTube (or similar). One post I realized I skipped was how to generate the first image of a face. So I explain how I approached that with ComfyUI, as well as exploring ways to turn the … More ComfyUI Stable Diffusion Image Generation
In this series of blog posts, I am working through steps to create consistent character AI generated videos using ComfyUI. I started with a 2D image of a face. The best advice I have seen recommends creating a series of images of the character with different facial expressions from different angles and using that to … More ComfyUI + Wan 2.1 VACE for Consistent Character Training Data
I have started the journey of trying to create consistent AI videos, using open source models and tools such as ComfyUI. There are some great online services around, but I am doing this all on my new shiny desktop with an RTX 5090. I need to justify my upgrade somehow! 😉 In a previous post … More ComfyUI Expression Editor for Consistent Characters
I (along with many others) want to use AI to create videos with consistent looking characters across shots. AI can generate some amazing shots, even with open source, but it frequently struggles with consistency. From my reading, if you have a 2D image of a character you like, you can improve the quality of AI … More ComfyUI IPAdapter First Attempt for Consistent Images
How to create movies or series with AI generated video? The AI tools are emerging at a rapid rate. The following is my current overall plan to leverage open source tools on my desktop. I should say up front it may be more sensible to use services. It can remove a lot of overheads to … More My Open Source Video AI Pipeline Plan (for this week at least)
Extra Ordinary, the Series 