Hey everyone!
We're releasing our Video Upscaling Workflow that transforms low-resolution footage into HD, 2K, or 4K quality using local AI processing.
What Makes This Different
By combining WAN 2.2 with the Ultimate SD Upscaler, we've built a generative AI upscaling solution that actually generates new detail and information instead of just interpolating pixels. You get genuine quality enhancement that surpasses traditional sharpening algorithms and even...
2025-11-25 13:39:59 +0000 UTC
View Post
Hey everyone I'm sorry I've been so quiet here and on discord for the last 10 days, but there was a reason:
I gave a TED TALK about the future of filmmaking!
What happens when AI makes filmmaking easier than ever? Will we see wild new narrative forms and stories from voices who never had the tools before, or will we drown in an ocean of meaningless AI slop?
In my talk, I share why I'm genuinely optimistic and what will really count in the future.
I'm n...
2025-11-18 11:59:46 +0000 UTC
View Post
Hey everyone!
Just dropped a new workflow that lets you create entire AI films shot by shot with consistent characters and locations. No LoRA training needed!
This one's special because it actually feels like real filmmaking. You can move your camera around 360-degree environments, swap out characters and locations instantly, and direct scenes with simple text prompts. Any style works: realistic, anime, claymation, you name it.
This workflow is built on Qwen Image Edit and t...
2025-11-01 09:18:23 +0000 UTC
View Post
Hey Everyone!
I'm currently working on a new AI filmmaking workflow that I think you'll really like! One part of it will be the ability to accurately move the camera around in your scene.
For that, I wanted to see if the Qwen Image model could generate 360-degree equirectangular images, but unfortunately the results weren't great.
Advanced workflows for: https://youtu.be/PhiPASFYBmk
Thank you so much for your support and making these videos possible!
If you have issues, questions, or ideas please let me know on our discord channel!
🔗 Download the ADVANCED VERSIONS & EXAMPLE FILES below!
Have fun generating!
251119 UPDATE 3.7
Unfortunately, due t...
2025-10-07 16:15:15 +0000 UTC
View Post
Creating hyperrealistic consistent characters is now easier than ever - and it's completely FREE!
All you need is one input image in any style. With a single click, my workflow automatically generates a perfect dataset: high-resolution upscaled images in different settings and poses, complete with detailed captions. If you want, you can even load in pose references or dress your character using the virtual try-on section of the workflow.
All of this is based entirely on free, open...
2025-10-07 15:55:47 +0000 UTC
View Post
Hey everyone! I'm excited to share my latest workflow featuring Qwen Image Edit that now allows you to use multiple reference Images and trust me, this is a game-changer!
What is Qwen Image Edit?
Qwen Image Edit is an AI model that lets you modify existing images using simple text instructions. Want to add, remove, or alter elements while keeping the original style and quality intact? This is your tool!
The best part? No more craft...
2025-09-29 12:06:25 +0000 UTC
View Post
Recently, a new version of the Qwen Image Edit model was released, and it's better in every single way. It also allows for easier installation since we no longer need to rely on extra LoRAs for additional functionality. New features include:
I just made generating consistent characters & training Loras MUCH EASIER!
With the newest version of the Consistent Character Creator 3.1. you will now not only generate a set of varied images for lora training, it will automatically generate the whole dataset including detailed captions for you. Just drag and drop it into your favorite lora trainer like AI toolkit or Flux Gym and start training.
This version will also handle HYPER REALISTIC as well as STYLIZED CHARACTERS a...
2025-09-05 11:09:52 +0000 UTC
View Post
Thank you so much for your support and making these videos possible!
If you have issues, questions, or ideas please let me know on our discord channel!
👉 Check out the ADVANCED WORKFLOW GUIDE: https://mickmumpitz.ai/guides/actor-compositor-advanced
🔗 Download the ADVANCED VERSION below!
Have fun genera...
2025-08-29 14:20:47 +0000 UTC
View Post
This is the future of VFX!
You can now create entire animated AI worlds for your short films with this free AI filmmaking workflow! In this video, we’ll show you how to replace your video’s background using just a prompt or reference image—while keeping your original camera movement perfectly intact. Unlike static AI backgrounds, this workflow generates animated environments that interact with your footage, adding realistic shadows, ripples, splashing water, and more.
To put...
2025-08-29 14:09:57 +0000 UTC
View Post
Creating consistent characters is now easier than ever!
Thanks to a new AI model, we can create amazing character datasets from a single image. Unlike previous versions of my Consistent Character Creator, which required merging different models and custom nodes, this version is based on a single model architecture, making it easy to use and install.
The workflow is also modular! You can duplicate groups and adjust prompts to suit your specific needs and preferences.
![]()
2025-08-20 09:33:20 +0000 UTC
View Post
Thank you so much for your support and making these videos possible!
Here is the advanced AI VFX workflow for adding controllable creatures & consistent characters to any footage using just one reference image and Wan 2.1. VACE in ComfyUI.
Note that this is just the standard configuration using the base Wan 14B model + 14B Vace module, but you can also use other models like the 3b versions. Use it as a foundation and do whatever you want with it, make it your own! <...
2025-07-17 13:14:19 +0000 UTC
View Post
Discover how to add controllable creatures & consistent characters to any footage using just one reference image and Wan 2.1. VACE in ComfyUI.
This tutorial walks you through cutting-edge AI animation techniques that compete with expensive studio methods, including precise motion control using Blender and After Effects.
We'll show you these breakthrough AI video generation methods by creating a complete smartphone-shot short film featuring a magical crystal-cat-dra...
2025-07-17 13:04:15 +0000 UTC
View Post
Here's the advanced version of our 3D texturing workflow featuring inpainting for higher quality results and style control using reference images with ipAdapter.
Got feature requests? Drop them in the #advanced-workflows-help > 3D TEXTURING + 3D MODEL GENERATION channel!
We've also created a detailed GUIDE for the advanced workflow: https://mickmumpitz.ai/guides/3d-model-tex...
2025-06-11 13:03:04 +0000 UTC
View Post
Learn how to use ComfyUI, Blender, and the open-source Hunyuan 3D model to texture existing assets or generate entirely new 3D models for films, games, and VFX shots.
We’ve pushed the limits of Hunyuan 3D by combining it with high-quality image models like SDXL and Flux to massively boost texture resolution. It even works on models with existing UVs making it easy ...
2025-06-11 12:06:12 +0000 UTC
View Post
Thank you so much for your support and making these videos possible. ❤️
You can download the Advanced Video Workflow below. I also included the simple SDXL img2img+ ControlNet workflow that I used to turn the images into anime style.
I've also prepared a folder with example images, character LoRAs, and datasets.
The images include metadata so you can see exactly how we created the images and videos.
🚩 If you need anything else, please let me know on our Di...
2025-05-01 11:55:27 +0000 UTC
View Post
👇 Download the FREE workflows below.
👉 Download the ADVANCED workflows & example files here: [COMING VERY SOON]
📝A groundbreaking free & local AI video model is changing filmmaking, giving creators access to techniques once reserved for major studios. Using the open-source Wan2.1 video model, you can now replace actors, transform visual styles, generate new shots from text, and even change camera movements in existing footage—all without expensive equipment...
2025-05-01 11:41:43 +0000 UTC
View Post
Many of you have asked about the Flux Workflow I use. Well, over the last few months, I've gradually built one that grew larger and larger. I've now streamlined it to make it easy to install while still offering all the essentials:
Lora support (I always use this workflow to test character Loras I train with my Consistent Character Creator), ControlNet for full control over your compositions and character poses, Demon Detailer for insane fidelity and upscaling for high resolutions.
...
2025-03-19 16:35:10 +0000 UTC
View Post
Thank you so much for your support! ❤️
Here you can download the advanced workflows and "250307_3D2IMG_patreon.zip" including:
The Loras we trained for the short film
Example blender renderings
Example outputs with ComfyUI metadata
Blender character rigs
If you need anything else, feedback or support, let me know on our Discord Channel!
2025-03-07 11:22:00 +0000 UTC
View Post
Learn how to create AI movies, comics or children's books with multiple consistent characters, controllable poses and camera angles with this free ComfyUI-Blender workflow!
Solve the biggest challenge in AI image generation - keeping multiple characters and environments consistent while controlling camera angles and character interactions.
This tutorial shows our free workflow combining ComfyUI with Blender to create AI movies, comics, and virtual characters with unprecedent...
2025-03-07 10:36:25 +0000 UTC
View Post
UPDATE! February 26, 2025
I just updated the MV Adapter Part of the workflow, so make sure to download the newest versions of the workflow!
This should fix the issues that some people had with the MV Adapter Part of the workflow. Make sure to also check the troubleshooting section in the guide!
---
The best version of the Character Consistency Workflow is here!
PulID for Flux is a tool that lets you include faces from input images in image...
2025-01-26 11:03:23 +0000 UTC
View Post
Important: I highly recommend you switch to the newest version of the consistent character creator!
It is easier to install, much more flexible and better in every way! You can get it here: https://www.patreon.com/posts/136914275?utm_campaign=postshare_creator
Thank you so much for supporting the channel and my work! ❤️
Be sure to check ...
2025-01-20 17:50:52 +0000 UTC
View Post
UPDATE! February 26, 2025
I just updated the MV Adapter Part of the workflow, so make sure to download the newest versions of the workflow!
This should fix the issues that some people had with the MV Adapter Part of the workflow. Make sure to also check the troubleshooting section in the guide!
----
Learn how to create perfectly consistent AI characters with our upgraded free workflow!
The new Consistent Character Creator v01...
2025-01-20 17:42:52 +0000 UTC
View Post
Thank you so much for your support! This video took absolutely forever to make and it would not have been possible without you!
You can download the advanced workflow, example files and reference videos below.
The example outputs have the metadata in them so you can just drag and drop them into ComfyUI to recreate my prompts and workflow.
You can find the INSTALLATION GUIDE here: 2024-12-12 14:01:42 +0000 UTC
View Post
Want to create epic movie scenes right from your living room? All you need is a computer and this free AI workflow to transform your home footage into cinematic magic!
Discover how AI is revolutionizing independent filmmaking! In this tutorial, I showcase how to turn basic camera footage into breathtaking cinematic scenes using free AI video tools.
Want to add magic spells to your scenes or transform your backyard into an alien planet? I'll demonstrate these techniques while creat...
2024-12-12 13:38:33 +0000 UTC
View Post
I'm blown away by all the incredible talent that's joined our Discord community since my recent videos! We've got graphic designers, storyboard artists, VFX wizards, and passionate creators from all walks of life.
And I've been thinking - why not channel all this creative energy into something amazing? We're launching our second community project: a full AI short film! The theme and style are locked in (thanks to our Discord discussions), and now we're looking for passionate folks to br...
2024-11-18 17:09:58 +0000 UTC
View Post
Thank you so much for supporting the channel and my work! Be sure to check out our community Discord and let me know what you want to see next!
👉 You can find the INSTALLATION GUIDE here: https://docs.google.com/document/d/1Hjf1LwpEy2KVmKb0TU4cjkzIofdi6tCP7qI7Sr6NtZs/edit?usp=sharing
Below you can download:
Sample FLUX Training Data...
2024-11-01 11:49:19 +0000 UTC
View Post
Transform single reference images into consistent character sheets using this free ComfyUI workflow! Learn how to generate multiple angles, expressions, and environments for your AI characters with FLUX or SDXL.
Perfect for training custom character Loras, this workflow supports various art styles including Disney, Anime and Pixar-inspired looks.
The step-by-step tutorial covers installation, prompt optimization, and advanced features for achieving character consistenc...
2024-11-01 11:30:16 +0000 UTC
View Post
