- 353
- 4 798 724
Nerdy Rodent
United Kingdom
Registrace 18. 12. 2018
AI Tutorials since 2020. Learn Stable Diffusion, Generative AI, Large Language Models, AI Animation, Voice Cloning, Text to speech, VQGAN, StyleGAN, Style Transfer, Super resolution / upscaling, Inpainting, Outpainting and many other amazing AI tools. All provided in an easy-to-digest video tutorial format, ready for anyone to do at home :)
Nerdy Rodent is an AI enthusiast with over 30 years professional computing experience. Make this channel your go-to for anything related to Artificial Intelligence to benefit from all that experience for free!
Don’t forget to like, share & subscribe.
For the best AI experience at home on your own PC I suggest:
* Ubuntu 22.04 LTS
* A modern Nvidia GPU (16+ GB VRAM)
* 64+ GB RAM
* 2+ TB SSD
* CPU with 6+ cores
Nerdy Rodent - the OG AI tutor creating nerds from way before AI was suddenly cool 😉
Not suitable for children. Please use AI responsibly.
Nerdy Rodent is an AI enthusiast with over 30 years professional computing experience. Make this channel your go-to for anything related to Artificial Intelligence to benefit from all that experience for free!
Don’t forget to like, share & subscribe.
For the best AI experience at home on your own PC I suggest:
* Ubuntu 22.04 LTS
* A modern Nvidia GPU (16+ GB VRAM)
* 64+ GB RAM
* 2+ TB SSD
* CPU with 6+ cores
Nerdy Rodent - the OG AI tutor creating nerds from way before AI was suddenly cool 😉
Not suitable for children. Please use AI responsibly.
Hyper-SD - Better than SD Turbo & LCM?
The new Hyper-SD models are FREE and there are THREE ComfyUI workflows to play with! Use the amazing 1-step unet, or speed up existing models by using the LoRAs.
Better than LCM? Take a look for yourself and see!
Want to support the channel?
www.patreon.com/NerdyRodent
Links:
huggingface.co/ByteDance/Hyper-SD
== More Stable Diffusion Stuff! ==
* Installing Anaconda for MS Windows Beginners - czcams.com/video/OjOn0Q_U8cY/video.html
* Installing ComfyUI for Beginners - czcams.com/video/2r3uM_b3zA8/video.html
* ComfyUI Workflows for Beginners - czcams.com/video/VM9snsuoqBc/video.html
* Faster Stable Diffusions with the LCM LoRA - czcams.com/video/zrxd95Mxz24/video.html
* Make an Animated, Talking Avatar - czcams.com/video/Z7TLukqckR0/video.html
* Make A Consistent Character in ANY pose - czcams.com/video/SacK9tMVNUA/video.html
Better than LCM? Take a look for yourself and see!
Want to support the channel?
www.patreon.com/NerdyRodent
Links:
huggingface.co/ByteDance/Hyper-SD
== More Stable Diffusion Stuff! ==
* Installing Anaconda for MS Windows Beginners - czcams.com/video/OjOn0Q_U8cY/video.html
* Installing ComfyUI for Beginners - czcams.com/video/2r3uM_b3zA8/video.html
* ComfyUI Workflows for Beginners - czcams.com/video/VM9snsuoqBc/video.html
* Faster Stable Diffusions with the LCM LoRA - czcams.com/video/zrxd95Mxz24/video.html
* Make an Animated, Talking Avatar - czcams.com/video/Z7TLukqckR0/video.html
* Make A Consistent Character in ANY pose - czcams.com/video/SacK9tMVNUA/video.html
zhlédnutí: 10 356
Video
Pixart Sigma - Like ELLA, but for Low VRAM SDXL+ Resolutions in ComfyUI!
zhlédnutí 7KPřed dnem
Pixart Sigma was released recently, and while the main repo takes a little tweaking to run nicely on 24GB VRAM, ComfyUI comes to the rescue making it easy to run in just 6 GB! Like with ELLA, T5 encodings replace CLIP leading to increased prompt adherence. Inthis video I show you how to get going for FREE in ComfyUI, and compare SDXL vs Pixart Sigma. All this without one of those SD3 “no commer...
UDIO - Make Music From Text Prompts
zhlédnutí 5KPřed 14 dny
UDIO vs SUNO - here we go! Generating music from text has never been easier, and boy is this a lot of fun :) Enter your own lyrics, use AI generated ones, extend, remix and more! No install! Want to support the channel? www.patreon.com/NerdyRodent Link: www.udio.com/ More Stable Diffusion Stuff! * Installing Anaconda for MS Windows Beginners - czcams.com/video/OjOn0Q_U8cY/video.html * Installin...
ELLA - A Powerful Adapter for Complex Stable Diffusion Prompts
zhlédnutí 10KPřed 21 dnem
Diffusion models have made incredible strides in text-to-image generation, but they still struggle with dense, complex prompts that involve multiple objects, detailed attributes, and intricate relationships. Enter ELLA - the Efficient Large Language Model Adapter that's poised to revolutionize how diffusion models handle sophisticated prompts. This ingenious adapter equips text-to-image models ...
BrushNet - The Best InPainting Method Yet? FREE Local Install!
zhlédnutí 7KPřed 21 dnem
Inpainting with the latest BrushNet models for AI generation using stable diffusion is lots of fun! Get great results quickly thanks to both random and segmentation mask models - all for free on your own computer! Installation is quick and easy, so why not give it a go today? Want to support the channel? www.patreon.com/NerdyRodent Links: github.com/TencentARC/BrushNet huggingface.co/spaces/Ten...
AniPortrait - AI Audio-Driven Synthesis of Portrait Animations - Local Install!
zhlédnutí 9KPřed měsícem
Using python & AI for animation images is always something I find fun, and there's a new kid on the block - AniPortrait! Using the power of Stable Diffusion, this repo can create animated avatars with fairly minimal effort. There have been quite a few research advances over the years, and this brings us a step closer. Want to install some of the latest, cutting edge, AI research at home? Well n...
New IP Adapter Model for Image Composition in Stable Diffusion!
zhlédnutí 15KPřed měsícem
The new IP Composition Adapter model is a great companion to any Stable Diffusion workflow. Just provide a single image, and the power of artificial intelligence will analyse the very composition itself - ready for you use! Check out some of things you can do with it :) Want to support the channel? www.patreon.com/NerdyRodent Links: huggingface.co/ostris/ip-composition-adapter More Stable Diffu...
Style Transfer Using ComfyUI - No Training Required!
zhlédnutí 12KPřed měsícem
Visual style prompting aims to produce a diverse range of images while maintaining specific style elements and nuances. During the denoising process, they keep the query from original features while swapping the key and value with those from reference features in the late self-attention layers. Their approach allows for the visual style prompting without any fine-tuning, ensuring that generated...
Layer Diffuse in Forge WebUI & ComfyUI
zhlédnutí 9KPřed měsícem
Stable Diffusion normally doesn't make transparent PNGs, but now you can thanks to Layer Diffuse! Available for both Forge WebUI and ComfyUI, Layer Diffuse does much more than just create single images without backgrounds too. Links: github.com/huchenlei/ComfyUI-layerdiffuse github.com/layerdiffusion/sd-forge-layerdiffuse More Stable Diffusion Stuff! * Faster Stable Diffusions with the LCM LoRA...
IOPaint (Lama-Cleaner): A FREE & Simple Inpainting / Outpainting App!
zhlédnutí 12KPřed 2 měsíci
Previously known as lama-cleaner, IOPaint has had a whole bunch of updates recently to provide your with a FREE and Open Source app for object removal, replacement and outpainting. With it's clean and intuitive interface, you won't need to be bogged down by tabs or confused by noodles. It's so easy to use :) Updates include: * Support sd1.5/sd2/sdxl normal or inpainting model from HuggingFace *...
Gemma 7B in Oobabooga WebUI - Beats Mistral 7B and Llama2 13B Benchmarks?
zhlédnutí 7KPřed 2 měsíci
Gemma is a family of lightweight, state-of-the-art AI text generation models built by google from the same research and technology used to create their Gemini models, and it runs great in the Oobabooga text generation webui. Being lightweight it will run on consumer hardware, and it's benchmark results beat other popular models such as Llama2 13B and Mistral 7B! Come and chat to Gemma! 🙃Want to...
WebUI Forge Integrated Basics + Proteus V0.3 Release!
zhlédnutí 16KPřed 2 měsíci
Stable Diffusion WebUI Forge is an optimised version of the A1111 WebUI, making SDXL use better for many! This makes it a great time to test out some SDXL models, including the recent Proteus V0.3, to see which may be best for your needs. Forge also comes with loads of integrated extensions, so I delve into the best of them to show how they work, what they do and why you should use them. Yes, y...
Is Stable Diffusion WebUI Forge Just Plain Better Than A1111 WebUI?
zhlédnutí 76KPřed 2 měsíci
Stable-Diffusion-WebUI-Forge is just plain better than Automatic1111. There. I said it :p Why? Well, performance and resource usage to start with. Even better still, some of the oldest bugs related to model loading have gone, plus you get loads of stuff just built right in! All that complete with the familiar A1111 WebUI gradio interface. Sure seems better to me! Want to support the channel? ww...
SegMoE - The Stable Diffusion Mixture of Experts for Image Generation!
zhlédnutí 11KPřed 2 měsíci
Mixture of experts. Seems hot for AI text generation... but what if you had a mixture of experts for IMAGE generation? Oh. Segmind just did that. Welcome to SegMoE - the mixture of experts for SDXL, SDXL Turbo and Stable Diffusion 1.5. Want to support the channel? www.patreon.com/NerdyRodent Links huggingface.co/segmind github.com/segmind/segmoe github.com/segmind/segmoe/blob/main/segmoe_config...
PhotoMaker - better than IPAdapter?
zhlédnutí 38KPřed 3 měsíci
Photomaker - create photos, paintings or avatars for anyone in any style within seconds! Quicker and easier than training a LoRA... but how good it is? Can it beat IPAdapter? You decide! Works great locally on Linux, MS Windows and Mac - or via a Huggingface space for the non-techies / those without hardware! Unlike InstantID (which can’t be used for commercial purposes = no pay-for installers,...
Animagine XL 3.0 - Is This The Best SDXL Anime Model Yet?
zhlédnutí 12KPřed 3 měsíci
Animagine XL 3.0 - Is This The Best SDXL Anime Model Yet?
AnyText - Easy Text Generation Using Stable Diffusion!
zhlédnutí 10KPřed 3 měsíci
AnyText - Easy Text Generation Using Stable Diffusion!
MotionCtrl Offers Custom Camera & Object Motion Controls for AI Animations
zhlédnutí 9KPřed 4 měsíci
MotionCtrl Offers Custom Camera & Object Motion Controls for AI Animations
Will AnimateDiff v3 Give Stable Video Diffusion A Run For It's Money?
zhlédnutí 18KPřed 4 měsíci
Will AnimateDiff v3 Give Stable Video Diffusion A Run For It's Money?
Exploring ComfyUI Latent Noise Control with Unsampler!
zhlédnutí 17KPřed 4 měsíci
Exploring ComfyUI Latent Noise Control with Unsampler!
From Stills to Motion - AI Image Interpolation in ComfyUI!
zhlédnutí 26KPřed 4 měsíci
From Stills to Motion - AI Image Interpolation in ComfyUI!
MagicAnimate Makes Images Dance - Install Locally or Remote Run!
zhlédnutí 30KPřed 4 měsíci
MagicAnimate Makes Images Dance - Install Locally or Remote Run!
ComfyUI Workflow Creation Essentials For Beginners
zhlédnutí 22KPřed 5 měsíci
ComfyUI Workflow Creation Essentials For Beginners
This One Simple Plugin Adds Realtime AI Assistance to Krita
zhlédnutí 53KPřed 5 měsíci
This One Simple Plugin Adds Realtime AI Assistance to Krita
3 Amazing and Fun Updates - ComfyUI and A1111 WebUI!
zhlédnutí 22KPřed 5 měsíci
3 Amazing and Fun Updates - ComfyUI and A1111 WebUI!
Generate up to 60% faster than base SDXL with less compute power!
zhlédnutí 11KPřed 5 měsíci
Generate up to 60% faster than base SDXL with less compute power!
How To Use AnimateDiff for Video To Video in ComfyUI
zhlédnutí 20KPřed 6 měsíci
How To Use AnimateDiff for Video To Video in ComfyUI
Realistic Face Swap with Stable Diffusion | EasyPhoto sd webui A1111
zhlédnutí 32KPřed 6 měsíci
Realistic Face Swap with Stable Diffusion | EasyPhoto sd webui A1111
@NerdyRodent hi I was trying to train this GAN-Control. I am having problem with training controller which is the last part of training. Can you please help me with this?
hi there, excellent tutorial, i keep finding an error about "Ipa Weight" when running the creative batch node, any ideas? i already updated comfy and nodes but the error keeps appearing.
ipa_weight for ipadapter should be a float value, so I'd start by checking that nothing says "NaN" or has text where a number should be
how much VRAM of gpu do you have? I have a 4070 with 12gb and it shows a cuda allocation error :/
why i cant have the option using "gpu" and not "cpu" ? the output is the same initial video and pc slow !! even if 17 12 + gpu rtx 3080 !!!
lol i spat out my drink at the perfect human hand part! LOL that's such a realistic human hand! XD
Thanks for this! Outro song is bomb and you're always great content. I love the ability to quickly generate decent images on one pass. Suggestion: it would be interesting to see a "low vram" e.g. 6GB workflow taking the 1 step generations with this model and then working those into more detailed images.
Great, superfast with IPadapter!
Bro I get conversion error
cool. love unconventional things like this! thanks
I can't express how much i despise pixel art, despite being one of those who used Spectrum-ZX. Who are those weird ppl that fall for this absurdly outdated way of displaying things while having all this technologies?
Couldn't get it running in A1111. :-(
Thanks buddy! Especially caught your words that PixArt generates more different faces than SD. These identical smiling cute ladies with almond-shaped features are already starting to get annoying, and it has not even been a year. I have installed PixArt at my place, I'm studying it now, but the first results are impressive.
I tried it for a little bit with A1111, the 8steps can be really useful but it's quite limited on sampling methods -- DDIM works good, others may vary and a few will simply destroy the result. Tried the 1step and it was a mess.
Yup, ddim sgm uniform is the best
Hi, I saw that you choose the Proteus-Rundiffusion model, for SDXL, but they have also a model withoutCLIP...If you run the prompt again, with the same settings, you will get your Rodent Detective! Also (rodent:1.4) works too! 😀 So it's not Proteus, but the version of Proteus. czcams.com/video/LAQYZWbmkwA/video.html
Yup - if you’re not getting the results you expect, try switching models!
@@NerdyRodent Thanks for your comment, Nerdy!
do you have a workflow which has pixart and controlnet and ipadapter?
China No.1
Works in forge and A1111 alongside controlnet ip adapter face id, tested it in 4 steps SD 1.5
1111webUIで使えますか??
03:56 Trump fish riding a bike!
ROFL, is it just me or is that outro song worth the price of admission all by itself?! I wouldn't be surprised if people started tuning in regardless of what the future videos will be about, just to check out the new outro. . Keep up the excellent work Nerdy, u crushin it my man...err crushin it, my Furry Nerdy Friend!
😉
quality > speed
Hi. Could you recommend a good video enhancer? Thanks
Nerdy really is the geezer! Cheers, mate
😉
I wonder how this would perform on a measely 4GB VRAM system like mine
What I am looking for is an AI to make parody songs. I have lyrics written and want AI to use the original artist's voice with my lyrics and overlay them on a karaoke version that is in that song's original style.
Yup, you can easily convert your voice with whatever lyrics you like in your chosen voice!
@@NerdyRodent I wrote a parody of Blurry by Puddle Of Mud and also a song by Tonic. Can AI analyze the original music videos or do they need spoken voices with no music to recreate them?
Spoken or singing voices are fine!
What's it like vs lightning?
Better 😉
They compared it with 1 step, but even though it didn't follow the prompt well, it still looked the best aesthetically, and usually you would use 4-8 step with lightning and get high quality results fast, plus you kinda showed that 8 step is preferable with hyper-sd anyway. I'll take your word for it though
Sooo... Better or not better ?
Do you compare fp16 is faster ?
How to make it run faster ? I want to use with canny CN and webcam image in RT )) I mean I have the same speed 1or 2 fps in sec on 3090
The 8 step XL lora works well in A1111, but you need to play with the weight 0.8-1 and Sampling method
Thanks. Yes the 8 Step Sdxl one seems to work pretty okay with Sd Forge also. But nothing else.
@@dreamzdziner8484there is a new lighting model, 3 steps! It works well in forge too CreaPrompt_Lightning_Hyper-SDXL
the udio outrow ẃas epic
Could you not do something like, full strength lora on step 1, and then with the lora off on steps 2-4, and get 100% quality?
Thank you sir.
Most welcome!
does it work with automatic 1111?
A1111?
the 8 step XL lora works well in A1111
It's only available on comfy? Dear God why?!
maybe because it's so super awesome?
with all respect of course
just bite the bullet and learn it. It's so good.
@@SetMeFree Agreed!
May I ask the author, where can I download the workflow demonstrated in your video? Thanks
You can get my modified workflows from www.patreon.com/NerdyRodent
Seems interesting, but lightning models already do similar stuff and they are easily compatible with other uis like a1111.
Good job this is so much better than lightning!
Hyper-SD works well with Krita live generation. 60 rodents per minute. Thank you for sharing!
Nice 👍🏽
That outro song is phenomenal.
😄
@@NerdyRodent just say the word oooohhh! su su su udio
Can you make a video about HiDiffusion?
Its not out yet for any UI but as soon as it is I also want to see this. Im keeping an eye out and hoping it gets released soon
Can this be used with Forge as well, or is it only working with ComfyUI?
works on Forge and A1111
Additional loras work?
Give ‘em a go!
Yes.
That fucking outro sound lol
😉
Los fucking canguros
But does it blend?
Almost certainly!
i am trying to do some experiments , will it work with either ipadapter or faceid , have anyone tried it
Does this wf still hold up with all the recent changes?
Yup! The plus face one is still the best that isn't for research-only use :)
t5 model is showing as unidentified even after putting it in right folder , any help , i also placed it in ella-embedd folder
Thanks for the great content! What I wasn't sure about was if I already have comfyui Install up and running, can I just skip the preparation step and move directly to step two? Thanks!
Yup, the video assumes you’ve got ComfyUI installed already 👍🏽
This new model is great. Thanks Rodent! .git directory in pixart_sigma_sdxlvae_T5_diffusers have extra 20 GB. Can be deleted.