![Stephan Tual](/img/default-banner.jpg)
- 24
- 126 727
Stephan Tual
United Kingdom
Приєднався 10 гру 2013
#ai #videos #stablediffusion #tutorial #comfyui #genai #animatediff #zeroscope
Learn Stable Diffusion and Comfy! Free workflows (evidently)
🤗🤗 Help keep this channel independent: ko-fi.com/stephantual 🤗🤗
👾 Stable Diffusion News: every two weeks
👾 Quick worflow tips: when they come
👾 Full worklow tutorials: when our tentacles allow
Join the discord: tinyurl.com/URSIUM
Hire actual extra-terrestrials: ursium.AI
Contact: my email is on this page somewhere
Learn Stable Diffusion and Comfy! Free workflows (evidently)
🤗🤗 Help keep this channel independent: ko-fi.com/stephantual 🤗🤗
👾 Stable Diffusion News: every two weeks
👾 Quick worflow tips: when they come
👾 Full worklow tutorials: when our tentacles allow
Join the discord: tinyurl.com/URSIUM
Hire actual extra-terrestrials: ursium.AI
Contact: my email is on this page somewhere
SUPIR Definitive Tutorial for Creative Upscaling
How to get perfect upscales with SUPIR. I tried answering all the questions you sent me in DMs :)
SUPIR worfklow: flowt.ai/community/supir-v2-plugandplay-edition-n5acf-v
▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬
00:00 Intro
01:16 SUPIR upscales complete guide
11:04 How to restore compressed images
15:38 Memetastic 1500% upscale
16:44 Upscaling AI generated images
19:28 Restoring old, damaged photographs
22:04 Adding details to an image like magnific
▬ SOCIALS/CONTACT/HIRE ▬▬▬▬▬▬▬▬▬▬▬▬
Discord: discord.gg/aJ32TNMnSM
All socials: linktr.ee/stephantual
Hire Actual Aliens: www.ursium.ai/
▬ LINKS REFERENCED ▬▬▬▬▬▬▬▬▬▬▬▬
S_noise and DPMPP_ETA: sandner.art/sigma-and-eta-noise-image-variations-in-latent-space-and-fast-detail-effects/
SUPIR worfklow: flowt.ai/community/supir-v2-plugandplay-edition-n5acf-v
▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬
00:00 Intro
01:16 SUPIR upscales complete guide
11:04 How to restore compressed images
15:38 Memetastic 1500% upscale
16:44 Upscaling AI generated images
19:28 Restoring old, damaged photographs
22:04 Adding details to an image like magnific
▬ SOCIALS/CONTACT/HIRE ▬▬▬▬▬▬▬▬▬▬▬▬
Discord: discord.gg/aJ32TNMnSM
All socials: linktr.ee/stephantual
Hire Actual Aliens: www.ursium.ai/
▬ LINKS REFERENCED ▬▬▬▬▬▬▬▬▬▬▬▬
S_noise and DPMPP_ETA: sandner.art/sigma-and-eta-noise-image-variations-in-latent-space-and-fast-detail-effects/
Переглядів: 16 181
Відео
SDXS: 90 millisecond renders with comfyUI
Переглядів 3,5 тис.2 місяці тому
Came for a config file, stayed for the hundreds of cute animals. Workflow & Models for download (or Plug&Play cloud) at: flowt.ai/community/sdxs-0.09-second-per-image-bjabe-v ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Introduction to the Kittens 01:09 Autoqueuing Bears 02:31 Running comfyUI in verbose mode 03:00 Editing the Yaml 04:09 Running the clean instance 04:45 Re-testing - 100 bears in 12 seconds! ...
A Brief History of Emad Mostaque at Stability.AI
Переглядів 1,7 тис.3 місяці тому
The root of all evil is the worship of money. To the worried community: It's going to be fine. ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Intro 00:26 Early shenanigans 01:03 Alledged embezzlement 01:45 The mass brain exodus 02:03 Money wasn't a thang for Emad 02:30 The point of no-return 03:13 Selling Holodecks to the gullible 04:38 Reinventing the wheel for profit 05:02 Under New Management 05:49 Emad re...
Perfect upscales with SUPIR v2 + full comfyUI workflow
Переглядів 20 тис.3 місяці тому
How to use SDXL lightning with SUPIR, comparisons of various upscaling techniques, vRam management considerations, how to preview its tiling, and even how to fix error messages you might encounter. Workflow, updated on 3/29/24 with LORAs and Lightning: flowt.ai/community/supir-v2-plugandplay-edition-n5acf-v ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Intro and results 00:51 Building the worklow 07:45 Going...
Video Generation w/AnimateDiff LCM, SD15 and Modelscope + any upscale!
Переглядів 6 тис.3 місяці тому
Let's explore how to make some creative photorealistic AI videos using AnimateDiff LCM, SD15 in conjunction with the brand new modelscope nodes, including humans. Also includes an update on the video generator I'm building (SVD AD Modelscope) AND an old video restoration tool! Workflow: flowt.ai/community/universal-video-generator-and-upscale-v4-lgdkt ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Introductio...
"NOT SORA" - Zeroscope In Depth - full Workflow & Tutorial
Переглядів 6 тис.3 місяці тому
I've spent way too much time generating 1000's of videos and I'm not SORA (get it?) hahah I need to sleep discord.gg/aJ32TNMnSM Workflow (v4) is at flowt.ai/community/universal-video-generator-and-upscale-v4-lgdkt-v 🤗Help keep this channel brutally honest: ko-fi.com/stephantual ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Introduction 00:30 Overview of Zeroscope/Modelscope 01:32 Required downloads and insta...
Stable Diffusion GenAI Breakthroughs & News - March 2024
Переглядів 2,6 тис.3 місяці тому
Discover this month Top 10 Innovations in Stable Diffusion! Updates in real time / share your work: discord.gg/aJ32TNMnSM 🤗Help keep this channel brutally honest: ko-fi.com/stephantual ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 - Quick intro 00:17 - Stable Cascade - is it the end-all be all? (no) 02:03 - Comfy Lighting support and models 02:59 - Layer Diffusion & Layout Learning 04:02 - Stable Diffusion 3...
SUPIR: Best Stable Diffusion Super Resolution Upscaler + full workflow.
Переглядів 18 тис.4 місяці тому
Install and build a worflkow for SUPIR, the HOT new Stable Diffusion super-res upscaler that destroys every other upscaler (again). Or does it? discord.gg/aJ32TNMnSM 🤗Help keep this channel brutally honest: ko-fi.com/stephantual Workflow: flowt.ai/community/supir-v2-plugandplay-edition-n5acf-v Do not buy workflows: it's a grift that hurts creators like myself (and your wallet) ▬ LINKS REFERENCE...
Magnific/Krea in ComfyUI - upscale anything to real life!
Переглядів 10 тис.4 місяці тому
Recover detail or bring video games characters to life! discord.gg/aJ32TNMnSM. Designed for you to learn how to use comfy effectively and make use of essential nodes so that you can debug it on your own. 🤗Help keep this channel brutally honest: ko-fi.com/stephantual Workflow/models/etc - (free, evidently) at: comfyworkflows.com/workflows/8e351973-ffc4-4d1b-bc09-ee38ee655804 ▬ TIMESTAMPS ▬▬▬▬▬▬▬...
Clean ComfyUI workflow in 3 minutes - no more ugly noodles!
Переглядів 2,4 тис.4 місяці тому
Clean up your noodles and create easy to scale up workflows. discord.gg/aJ32TNMnSM 🤗Help keep this channel brutally honest: ko-fi.com/stephantual ▬ LINKS REFERENCED ▬▬▬▬▬▬▬▬▬▬▬▬ github.com/rgthree/rgthree-comfy ▬ SOCIALS/CONTACT/HIRE ▬▬▬▬▬▬▬▬▬▬▬▬ Discord: discord.gg/aJ32TNMnSM All Socials: linktr.ee/stephantual Hire Actual Aliens: www.ursium.ai/
Upscalers Roundup + Full Workflow - LDSR, Ultimate SD, Models, HiRes Fix, Latent Upscale + Topaz
Переглядів 10 тис.4 місяці тому
What's the best upscaler in comfyUI? discord.gg/aJ32TNMnSM Download the worfklow, all the files in the video, and the prompts at: comfyworkflows.com/workflows/c907d7ad-5ea4-4b05-8f10-040ab57b4ea4 🤗Help keep this channel brutally honest: ko-fi.com/stephantual ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 - What did I test? 00:35 - Getting started & worfklow introduction 01:20 - Important upscaler basic concep...
How to run only one branch of a comfyUI workflow (in 60 seconds)
Переглядів 2,1 тис.4 місяці тому
Don't re-render uncached nodes! Use RGThree to render only one branch at a time, saving yourself a good 10 minutes on that LDSR upscaler :) discord.gg/aJ32TNMnSM 🤗Help keep this channel brutally honest: ko-fi.com/stephantual Full worfklow available as part of my free long form tutorials. ▬ LINKS REFERENCED ▬▬▬▬▬▬▬▬▬▬▬▬ github.com/rgthree/ ▬ SOCIALS/CONTACT/HIRE ▬▬▬▬▬▬▬▬▬▬▬▬ Discord: discord.gg/...
What's new in comfyUI - February 2024 - new nodes, models, tools!
Переглядів 6 тис.4 місяці тому
Episode 2 of "What's new in Stable Diffusion" - discord.gg/aJ32TNMnSM Subscribe to keep up with the latest ComfyUI trends and innovations! 🤗Help keep this channel brutally honest: ko-fi.com/stephantual ▬ TIMESTAMPS ▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 - Intro 00:27 - The AI Apocalyse is upon us 01:12 - Dynamic Crafter 01:45 - AnimateDiff major update (again) 02:00 - Preview of week 3 (Stable Cascade AD) - Tx Ban...
The numbers game behind making AI videos with #comfyUI
Переглядів 5654 місяці тому
How do AI creators generate images & videos today? It's a number's game - NOT a question of 'prompt'. In this video we explore how VFX artists like @BryanHoward use comfy as part of their workflow, we touch on photorealism with Blender and why AI INTEGRATION, not REPLACEMENT is the way forward. And I criticize SORA a little more, because I can. 🤗Help keep this channel brutally honest: ko-fi.com...
The bug that's a feature in ComfyUI - batching and Ksampler noise!
Переглядів 8634 місяці тому
The bug that's a feature in ComfyUI - batching and Ksampler noise!
OpenAI SORA killed comfyUI and ALL generative AI competition... or has it?
Переглядів 1,1 тис.4 місяці тому
OpenAI SORA killed comfyUI and ALL generative AI competition... or has it?
1-node Watermark + Intro to comfyroll - in 2 minutes!
Переглядів 6324 місяці тому
1-node Watermark Intro to comfyroll - in 2 minutes!
LDSR - best comfyUI upscaler - results at 4k.
Переглядів 4 тис.4 місяці тому
LDSR - best comfyUI upscaler - results at 4k.
Better worflows: RGthree Fast Group Muters
Переглядів 1,5 тис.4 місяці тому
Better worflows: RGthree Fast Group Muters
Installing ComfyUI start to finish in Feb 2024 - beginner Tutorial w/ best practices.
Переглядів 2,7 тис.4 місяці тому
Installing ComfyUI start to finish in Feb 2024 - beginner Tutorial w/ best practices.
This Week in ComfyUI / Generative AI (SVD1.1, MotionDirector, AnimateLCM, ControLLLite, and more!)
Переглядів 3,1 тис.4 місяці тому
This Week in ComfyUI / Generative AI (SVD1.1, MotionDirector, AnimateLCM, ControLLLite, and more!)
1h of State of the Art ComfyUI Q1 2024 - IPAdapter, AnimateDiff v3 Gen2/ControlNets/Reactor + more!
Переглядів 3,1 тис.5 місяців тому
1h of State of the Art ComfyUI Q1 2024 - IPAdapter, AnimateDiff v3 Gen2/ControlNets/Reactor more!
Greetings, I have tried it with Matrix, Pinokio and the portable. Maybe they are compatibility problems but the "SaveVideo" nodes do not load. I don't know how many the same thing has happened to.
Is there such thing as buying a PC with ComfyUi already installed..?
i have error error occurred when executing supir_upscale
Doesn't work. Image Resize node has red outline almost immediately, no idea why: Error occurred when executing ImageResize+: 'bool' object has no attribute 'startswith'
Very useful information ! Thanks!
ahahahah the owl tutorial joke killed me
great job, but for render video we need quantum pc...
Hi Stephan ! Whare are you been ? 2 months we haven't seen you Dude.
I want you to know how much this is appreciated. Thank you.
I think I upscaled my brain after watching this. Thanks bro.
super bien fait mec merci beaucoup 💙
Thank you for explaining the whole process with every little detail. Loved that you got the example of someone that could be any of us and showed why it didn't work and how to fix it. Please continue like this!
Does this work for Animatediff too?
Thank you so much for your lessons, I made a short AI film using your lessons, I set up IPADAPTER and AnimateDiff and got an amazing result, I like it very much ua-cam.com/video/MFmTsgkLXRA/v-deo.html
Great video, Stephan! I've been using ComfyUI for about a week now. Everything was working well for the first couple of days until this 'reconnecting' error started to appear whenever ComfyUI is loading a checkpoint. Initially, I thought it might be a memory issue, but it's not even loading the VRAM usage. Do you have any suggestions on how to fix this? Thanks in advance!
Thanks!! Great content!! 😊
ComfyUI is literally the least comfy ui I've ever seen. What a piece of hot garbage.
I am a little confused by one thing. The SUPIR Sampler Node seems to support only DPM++2M and EDM Samplers. Quite a few of the faster models are optimized for DPM+ + SDE, Euler A, or another sampler. On some models it makes a huge difference. Does this matter a lot for the SUPIR model? Should we spend time testing a model we want to use with SUPIR with DPM++2M and/or EDM ahead of time? SUPIR can be quite slow, so I'd like to make sure that the issue is not simply a question of model/sampler compatibility. Thanks
Someone told me that the portable version is using python_embedded and some nodes che be installed wrongly, while a venv installation should be preferred. Is that any good as advice?
Were do we import our image?
I'm impressed! Big thanks for your effort and your time to spend in this video. For me, it's a bit to fast and I have to stop and play it again... but its very helpfull!
The one thing I do not like about SUPIR is that it's not for commercial use.
It's strange, you have a French accent...
Hi Stephan, I have used your workflow for some time now and everything worked flawless so far, but since I've updated comfyui and the nodes today I get an error when it comes to image resizing: Error occurred when executing ImageResize+: 'bool' object has no attribute 'startswith' Any idea how to solve this?
Can you use supir for video upscaling? Would it stay consistent or not really?
cut and paste for xformers did not work for me. Copy paste should be: python.exe -m pip install -U xformers --no-dependencies This is what is shown in the video @1:20, but is not in the C/P text.
Amazing! I need more of there compare vids
how to run run_nvidia_gpu.bat?
how to show CPU, GPU, RAM and VRAM like your Comfyui?
The size of the source image is 2048 * 2048. How to divide it into tiles? The image generated after I divide it into tiles is also divided, not the entire image. What settings are wrong?
please link Civitai
why don't you show the final node where the image preview is shown. what is that node? jumping around aint helping. take it slow, and make it clear dude.
I think it is Image Comparer (rgthree)
@@ArmanVesona yes that's the one.
Great video. Thanks for the effort
Hello, This is this first workflow that really works (at least for me), thank you! I wrote you already I was looking for img2img workflow to get a realistic skin other than upscaling, this work perfect! I'm now trying with different Loras to achieve what I want, thank you again! Just a thing, the SUPIR Conditioner node doesn't have a positive prompt but just the negative, in the workflow I downloaded. EDIT: I realized now I have downloaded the next version you did :)
Thank you! This works well for just redoing an inpainting group without having to have a seed fixed for the original output!
Hello and thanks for the video! Do it exist a easier wotkflow, this one is huge for a newbie as I am :), just to make face skin more realistic and less plastic? Just an img2img to add detail and do a skin more realistic :)
Great content! Can you create more content like this to catch a noob up on the drama of the industry? Particularly interested in feasibility of decentralized AI.
People have better results because they do have skill and you don’t. It works same everywhere, if you are dumb and lazy, do not expect something good come out just because you wasted full time on that.
Topaz tends to make swirls from details, and make thin features like fingers look like smudged water painting streaks. It's not worth it at all, I wouldn't use it even if it was free.
Sadly when trying to upscale the Video Game character, it is not changing it to REAL LIFE. just upscales it as it is.
The node graphs = Indian telegraph poles..... Functional ? maybe
These workflows cannot be refined and simplified?
But, is that a different supir workflow, where you enhance and add details to the cute doll image at the end?? from 22:10 ??
I am looking for a Windows executable for a SUPIR upscaler with just a handful of options. Has anyone found anything like that yet? I found some for REALESRGAN, so I figured there might be at least one for SUPIR, seeing how awesome it is.
If you could show one example for an architecture image, I would love you forever...!
"Theres nothing arbitrary about workflows" damn thats a good line lol
I only have a 3060 laptop but I can get some nice images with your workflows you are a god at tweaking settings and I learned how to do that myself now by watching you
Hi Stephan I really enjoy your videos thank you
18:13 where to get this other workflow?