AI image generation doesn't always need the best GPUs, as these 3 smaller models show. Smaller can often mean faster too, so even higher-end owners can benefit. Lumina 2.0 is great at following prompts, TinyBreaker uses an interesting mix of Pixart with Stable Diffusion, and Animagine XL 4 is the latest anime SDXL model in the series.
Want to support the channel?
https://www.patreon.com/posts/new-models-ideal-122400407
Links:
https://github.com/comfyanonymous/ComfyUI
https://github.com/Alpha-VLLM/Lumina-Image-2.0
https://comfyanonymous.github.io/ComfyUI_examples/lumina2/
https://github.com/martin-rizzo/ComfyUI-TinyBreaker
https://huggingface.co/cagliostrolab/animagine-xl-4.0
== Beginners Guides! ==
1. How to install and run Python environments on MS Windows - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflow Basics - https://youtu.be/VM9snsuoqBc
YuE now has a free and open source license, switching from non-commercial over to Apache 2.0. This means you can now make AI generated music at home, for free on your own computer with as little as 6GB VRAM and generation times of only 4 minutes!
No more running out of credits on websites 😉
Writing your own lyrics and style tags isn't your only control though, as you can also upload your own vocals, instrumental or both to serve as a prompt! Plus you can get vocal or instrumental stems as output to enable even more creative options. Make some music and then sing over it yourself without needing to separate the vocals, for example.
Various options for using YuE are available, and I compare some of them here.
Want to support the channel?
https://www.patreon.com/posts/yue-foss-music-121804728
Links:
YuE Project - https://map-yue.github.io/
YuE GitHub - https://github.com/multimodal-art-projection/YuE
YuE for Windows - https://github.com/sdbds/YuE-for-windows
YuEGP - https://github.com/deepbeepmeep/YuEGP
YuE-exllamav2 - https://github.com/sgsdxzy/YuE-exllamav2
Yue-exllamav2-UI - https://github.com/alisson-anjos/YuE-exllamav2-UI.git
VoC - https://softology.pro/voc.htm
Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
DeepSeek. It's a Large language model. Very large. Thankfully, there are smaller, distilled versions available to run at home for FREE :)
But how well does DeepSeek do when it comes to prompt generation for FLux.1 in ComfyUI? I guess it's time to find out!
* Want to support the channel? -
https://www.patreon.com/posts/deepseek-r1-flux-121216013
* Links:
https://github.com/comfyanonymous/ComfyUI
https://ollama.com/
https://ollama.com/library/deepseek-r1
https://huggingface.co/deepseek-ai/Janus-Pro-7B
== Beginners Guides! ==
1. A Beginner's Guide to Installing Python - https://youtu.be/OjOn0Q_U8cY
2. Properly Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflow Basics - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
* Speed Boost Flux, SDXL, LTVX or HunyuanVideo with TeaCache & WaveSpeed! - https://youtu.be/beiVSzsH2R0
* Using Detail Daemon in ComfyUI for Extra Details! - https://youtu.be/dG9HfgngsqM
Image to Video, Video to Video, Text to Video and Camera Controls. What more could you want from an AI video generation model? Maybe control using pose, scribble or depth videos? That's there too. How about trajectory based control? Also possible! Maybe you'd like camera control too? Is panning, zooming and rotating enough? And the license... Apache-2.0 license :)
Want to support the channel?
https://www.patreon.com/posts/image-2-video-120765322
== Links ==
GitHub - https://github.com/aigc-apps/EasyAnimate
Qwen VL Int 8 - https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== Flux.1 in ComfyUI ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
Nvidia Cosmos has a set of "world" models designed to generate synthetic data for training... but it can do so much more than that, such as animating images and even image interpolation! Oh, and it can generate rodents too.
Run it at home, for free, on your own computer with just 12GB VRAM. ~7 minutes for a 704x704 121 frame video :)
Want to support the channel? -
https://www.patreon.com/posts/image-2-video-in-120326825
== Links ==
Blog: https://blog.comfy.org/p/comfyui-now-supports-nvidia-cosmos
Example: https://comfyanonymous.github.io/ComfyUI_examples/cosmos/
Nvidia's Cosmos Video: https://www.youtube.com/watch?v=9Uch931cDx8
Ollama: https://ollama.com/
== Beginners Guides! ==
Step 1. Anaconda (python) Installation - https://youtu.be/OjOn0Q_U8cY
Step 2. Standard ComfyUI Installation - https://youtu.be/2r3uM_b3zA8
Step 3. An Introduction to ComfyUI Workflows - https://youtu.be/VM9snsuoqBc
== Flux.1 in ComfyUI ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* How to Train A Flux LoRA for FREE! - https://youtu.be/7AhQcdqnwfs
Faster image and video generation with SDXL, Flux, LTVX and Hunyuan Video is here thanks to the power of caches. Speed up a little - or a lot! TeaCache claims a 1.4x lossless speedup, and at a push I’m e found you can just about get to 3x speedup with images.
These handy ComfyUI nodes are quick to install, and then all you need to do then is pop a cache node into your existing workflow for an instant speed boost!
I put a couple of options through their paces, with some interesting results...
Links:
https://github.com/welltop-cn/ComfyUI-TeaCache
https://github.com/chengzeyi/Comfy-WaveSpeed
Want to support the channel?
https://www.patreon.com/posts/boost-sdxl-flux-119802818
== Beginners Guides! ==
ComfyUI has been around for a while now, but if you’re just starting your AI journey it’s a good idea to start at the beginning…
1. MS Windows Beginners Need Anaconda for Python - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Using Flux in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting with Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA for Free at Home - https://youtu.be/7AhQcdqnwfs
SillyTavern is a free user interface you can install on your computer (and Android phones) that allows you to interact with LLMs and other backend APIs. Super easy to install, even for the computer novice, and yet very powerful! Start the launcher. Press 1 to install!
Create your own tavern filled with characters of your choice. Give them all personalities, avatars and even individual knowledge via the data bank. Send and receive images too, now also powered by ComfyUI!
Lots has changed since my original video from a year ago - https://youtu.be/_2-KwnJPwfE - with extra features and support for many more APIs :)
Links:
https://github.com/SillyTavern/SillyTavern
https://github.com/SillyTavern/SillyTavern-Launcher
https://github.com/SillyTavern/SillyTavern-Extras
https://docs.sillytavern.app/
https://booth.pm/en/items/3072192
https://booth.pm/en/items/3853613
Want to support the channel?
https://www.patreon.com/posts/silly-tavern-in-119374883
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI using Anaconda - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
Contents:
0:00 Silly Tavern Introduction
0:40 Silly Tavern Install 2025
3:50 Silly Tavern LLM Setup
7:13 Silly Tavern Backgrounds
7:30 Silly Tavern Visual Novel
7:51 Silly Tavern Character Expressions
9:03 Silly Tavern Character Voices
11:04 Silly Tavern ComfyUI Integration
13:57 Silly Tavern Image Vision
15:17 Silly Tavern Live2D
17:45 Silly Tavern VRM
18:51 Silly Tavern Speech Recognition
22:32 Silly Tavern Data Bank (RAG)
Turn your images into stunning 2.5D parallax animations using Depthflow in ComfyUI. An open source Immersity alternative with loads of custom controls. Doesn't use much VRAM and is lightning fast!
And so ends 2024… see you in 2025! Happy New Year 🥳
Links:
ComfyUI - https://github.com/comfyanonymous/ComfyUI
DepthFlow - https://github.com/akatz-ai/ComfyUI-Depthflow-Nodes
Want to support the channel?
https://www.patreon.com/posts/happy-new-year-119018639
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. Making ComfyUI Workflows - https://youtu.be/VM9snsuoqBc
== Flux.1 ==
* How to use Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
Do you have multiple LoRAs and wish you could use them all for different areas? Well, the recent ComfyUI blog on Masking and Scheduling LoRA and Model weights introduces some new nodes to us making it super easy! With hooks you can now attach LoRAs to conditioning, rather than going through the typical model pipeline. New combine nodes also make it easier to work with conditioning pairs. Together they help to build simplified workflows for all sorts of regional prompting tasks :)
Links:
https://blog.comfy.org/masking-and-scheduling-lora-and-model-weights/
https://github.com/comfyanonymous/ComfyUI
https://github.com/logtd/ComfyUI-Fluxtapoz
Workflow Basics - https://youtu.be/VM9snsuoqBc
Flux Redux - https://youtu.be/1AlmHTFWjLk
RF Edit - https://youtu.be/6AHL0XZKbqg
Want to help support the channel?
https://www.patreon.com/posts/regional-loras-117960010
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
Hunyuan Video can be run at home, on your own computer with as little as 8GB VRAM. Create videos directly from a text prompt, or do video-to-video for more control. Runs nicely in ComfyUI!
Update: nf4 quant option now also available for the LLM 😀
== Links ==
https://github.com/Tencent/HunyuanVideo
https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
https://github.com/thu-ml/SageAttention
https://github.com/woct0rdho/triton-windows/releases
https://purz.notion.site/Get-Windows-Triton-working-for-Mochi-6a0c055e21c84cfba7f1dd628e624e97
Want to help support the channel? -
https://www.patreon.com/posts/hunyuan-video-in-117444104
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
== Contents ==
0:00 Hunyuan Video Intro
0:33 Linux Hunyuan Video ComfyUI Install
1:32 Windows Hunyuan Video ComfyUI Install
2:33 Hunyuan Video ComfyUI Usage
RF Inversion (unsampling) works well, but RF Edit gives you another tool in the toolbox for making image edits. Flux Regional Prompting lets you prompt specific regions, with PAG/SEG adding extra details and a little prompt adherence to your generations. Best of all, you get all three from the Fluxtapoz GitHub repo!
Run for free on your own computer at home, and let your imagination run wild!
Links:
https://github.com/comfyanonymous/ComfyUI
https://github.com/logtd/ComfyUI-Fluxtapoz
Want to support the channel?
https://www.patreon.com/posts/flux-regional-rf-117081391
== Beginners Guides! ==
1. Installing Anaconda (Python) for MS Windows AI Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
Contents
---------------
0:00 Fluxtapoz RF-Edit Workflow
6:38 Fluxtapoz InstantX Regional Prompting
12:07 Flux Perturbed Attention Guidance (PAG) and Smoothed Energy Guidance (SEG)
Black Forest Labs have dropped their latest models - Fill, Redux, Depth and Canny! Fill improves inpainting & outpainting, Depth & Canny give us the best results yet and Redux... well... that's my favourite :)
Want to support the channel? -
https://www.patreon.com/posts/new-flux-models-116475628
Links:
https://blackforestlabs.ai/
https://huggingface.co/black-forest-labs
https://comfyanonymous.github.io/ComfyUI_examples/flux/
== Beginners Guides! ==
1. Installing Python for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
The core concept of In-Context-LoRA (IC-LoRA) is to concatenate both condition and target images into a single composite image whilst using natural language to define the task - such as "put this design on a bag".
Whilst the paper and LoRAs concentrate on generating multiple panels at once, you can also inject your own images as the context too! 😃
Want to support the channel? -
https://www.patreon.com/posts/116127838
Links:
https://huggingface.co/ali-vilab/In-Context-LoRA
https://github.com/ali-vilab/In-Context-LoRA
https://arxiv.org/abs/2410.23775
https://comfyanonymous.github.io/ComfyUI_examples/flux/
https://comfyanonymous.github.io/ComfyUI_examples/lora/
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA using ai-toolkit - https://youtu.be/7AhQcdqnwfs
OmniGen does as the name suggests... generates images in a whole variety of different ways. Load an IPAdapter and a ControlNet into a workflow? Not me! I just want to load the one OmniGen model and go :) One thing is does well is to put multiple characters into a single scene - clothing included!
Looking to support the channel?
https://www.patreon.com/posts/omnigen-in-for-115746400
OmniGen GitHub - https://github.com/VectorSpaceLab/OmniGen
== Computing Beginner? Start here! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== Try Flux.1 in ComfyUI! ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
The EASY way to get more details in your ComfyUI generations - Detail Daemon! 4 new nodes and 3 great new ways to add those tiny intricacies, such as more detailed skin.
Want to support the channel? Consider becoming a Patreon!
https://www.patreon.com/posts/detail-daemon-115118785
== Beginner? START HERE! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== Even More Flux.1 ==
* How to use Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* Using AI Enhanced Prompts in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
* Make your own scheduler in ComfyUI - https://youtu.be/Sc6HbNjUlgI
It's Flux.1, but not as we know it! Various artistic styles are now at your fingertips, and it's all thanks to this fine tuned model... but is it any good?
Huggingface: https://huggingface.co/mikeyandfriends/PixelWave_FLUX.1-dev_03/tree/main
Want to support the channel? Workflows and more info available at
https://www.patreon.com/posts/pixelwave-flux-114819050
== Beginners Guides! ==
New to installing and running ComfyUI? Check these!
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
Need more flux info?
* Basic Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* ComfyUI Flux.1 Playlist - all you need to know!
https://www.youtube.com/playlist?list=PLjC8P1vEncQCsAVthI5T1jM0jRCn1H7EC
The wait is over... SD3.5 is finally here! Time to relax on the grass... or is it? Stable Diffusion 3.5 has a number of models, both distilled and non-distilled. Very handy for those who like to fine-tune! Expect some interesting models in the future :)
Want to support the channel?
https://www.patreon.com/posts/sd3-5-released-114515517
Stability AI: https://stability.ai/news/introducing-stable-diffusion-3-5
ComfyUI: https://github.com/comfyanonymous/ComfyUI
ComfyUI Examples: https://comfyanonymous.github.io/ComfyUI_examples/sd3/
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
Three new things this week with the release of two models from AliMamma along with some Rectified Flow Inversion (Unsampling from RF Inversion)!
Still using more than 8 steps and waiting minutes for your results? Slap the power of turbo in for extra fast image generation using Flux AND it works with RF inversion for amazing image edits! What are you waiting for? Not Turbo, that’s for sure 😉
Quickly and easily style any image. Turn anime images into realistic ones, or realistic images into cartoons… or 3d models, or wood, or… RF inversion is super versatile!
Nb. With recent ComfyUI updates, centre no longer centres and instead has become fit to view, but hey 🫤
ComfyUI: https://github.com/comfyanonymous/ComfyUI
ComfyUI Manager: https://github.com/ltdrdata/ComfyUI-Manager
AliMamma: https://huggingface.co/alimama-creative
Rectified Flow Inversion for Flux: https://rf-inversion.github.io/
Fluxtapoz: https://github.com/logtd/ComfyUI-Fluxtapoz
NR Huggingface: https://huggingface.co/datasets/NerdyRodent/NR-Flux-ComfyUI-Workflows
Want to help support the channel?
https://www.patreon.com/posts/comfyui-simple-114172494
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 in ComfyUI - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
With a super-simple interface, using this workflow for Flux.1 and Llama 3.2 couldn't be easier! No need to scroll around or look at any complex nodes - just have a conversation and make some images :)
Try these prompt examples!
Add more flowers, please
Give everyone a silly hat!
What is outside the window?
What is the main character thinking about?
ComfyUI: https://github.com/comfyanonymous/ComfyUI
ComfyUI Manager: https://github.com/ltdrdata/ComfyUI-Manager
Huggingface: https://huggingface.co/datasets/NerdyRodent/NR-Flux-ComfyUI-Workflows
Even more workflows on patreon!
https://www.patreon.com/posts/simple-llm-flux-113862301
== Beginners Guides! ==
1. Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
2. Installing ComfyUI for Beginners - https://youtu.be/2r3uM_b3zA8
3. ComfyUI Workflows for Beginners - https://youtu.be/VM9snsuoqBc
== More Flux.1 ==
* Flux.1 Released! - https://youtu.be/DLUx-mK4g0c
* AI Enhanced Prompting in Flux - https://youtu.be/4d5zIBNuMRA
* Train your own Flux LoRA - https://youtu.be/7AhQcdqnwfs
Conectar
