Latent VisionI updated the IPAdapter extension for ComfyUI. It's a complete code rewrite so unfortunately the old workflows are not compatible anymore and need to be rebuilt. Sorry about that but I don't have time to maintain old code.
IPAdapter v2: all the new features!Latent Vision2024-03-25 | I updated the IPAdapter extension for ComfyUI. It's a complete code rewrite so unfortunately the old workflows are not compatible anymore and need to be rebuilt. Sorry about that but I don't have time to maintain old code.
00:00 Intro 01:19 Flux sampler with parameters 05:06 Steps to converge 09:14 Samplers and Schedulers 13:41 Guidance 16:09 Base and Max Shift 19:36 Attention Seeker 23:41 OutroMath and conditions to build complex workflowsLatent Vision2024-08-27 | In this pill we are going to talk about Math, conditions, execution blockers and how I used them to build the Latent Upscaler.
00:00 Intro 00:26 Math Conditions 02:56 Advanced Math 06:06 Triggers 07:10 Latent UpscalerDeep dive into the FluxLatent Vision2024-08-15 | My analytical view of Flux. Its strengths, weaknesses and a few tricks to get the best out of it.
A few workflows to get you started, check them all, there are a few extras: https://f.latent.vision/download/flux.zip
00:00 Intro 03:46 Basic workflow 07:15 Prompt trouble with Art Styles 09:59 Sampler Flux with Parameters 15:37 Prompting 20:41 Anime bias 22:08 Noise injection 24:20 Image to Image 26:04 OutroBest cuts from July 22nd Stream!Latent Vision2024-07-24 | This is a shorter and more digestible cut of the 2h long Stream we had few days ago. We talked about: ClipVision Enhancer, Kolors IPAdapter, IPAdapter Mad Scientist, Face segmentators and their usage with AnimateDiff, IPAdapter Precise Composition and more!
00:00 ClipVision Enhancer 04:00 How the enhancer work 10:35 Enhance Ratio 16:47 Difference with Tiled IPAdapter 18:38 Rebuilding the workflow 31:14 The Tile node 34:02 Image2Video 35:08 Sponsorship and open source 37:00 Kolors IPAdapter 43:28 Precise Composition 49:52 Face segmentator 56:34 Face segmentator with AnimateDiff 59:38 Experimenting with the Mad Scientist 1:03:10 Inspirenet Remove BackgroundUpdates! ClipVision Enhancer, Kolors, Precise Composition and more!Latent Vision2024-07-22 | A streamlined version of this video is available here: youtu.be/RnfyYWQ8oM8
It has been a busy couple of weeks. I have updates for IPAdapter, the Essentials and Face Analysis. Let's talk about it!
00:00 Intro 00:49 It's just noise 03:40 ControlNet Canny 08:56 Tidy the mess 10:33 ControlNet OpenPose 11:50 OpenPose with full body 14:09 ControlNet Tile 15:29 Simple Upscale 18:11 Noise injection 22:18 Upscale with tiling 30:28 Upscale with model 33:55 OutroAdvanced Style transfer with the Mad Scientist nodeLatent Vision2024-06-24 | We are talking about advanced style transfer, the Mad Scientist node and Img2Img with CosXL-edit. Upgrade the IPAdapter extension to be able to use all the new features. Workflows are available in the example directory.
00:00 Intro 00:23 Style Transfer Precise 02:03 Mad Scientist Node 05:35 Advanced Blocks Tweaking 07:27 CosXL EditDissecting SD3Latent Vision2024-06-19 | How does SD3 work? Is it any good? No drama, no politics, only the technical side of things.
00:00 Intro 00:35 Default workflow 05:46 Testing the negatives 08:44 Lying in the grass 12:40 Prompt adhesion 15:19 Noise 16:30 High resolutions 17:28 Control Nets 18:41 LicenseHigher quality images by prompting individual UNet blocksLatent Vision2024-06-07 | This time we are going to do some R&D and I will need your help to reverse engineer the UNet. Basically prompting each block of the UNet separately with a dedicated prompt we are able to get higher quality generations.
Discord server: discord.com/invite/W2DhHkcjgn Github sponsorship: github.com/sponsors/cubiq Support with paypal: paypal.me/matt3o Twitter: twitter.com/cubiqAbout AI, Art, Ethics and the environmentLatent Vision2024-06-02 | Not a tutorial but this is something I wanted to talk about since a while. Ethics of using AI, the environmental costs and Is AI art? The subtitles are hand edited and corrected.
TED Talk by Sasha Luccioni: ted.com/talks/sasha_luccioni_ai_is_dangerous_but_not_for_the_reasons_you_thinkHow to use Face Analysis to improve your workflowsLatent Vision2024-05-24 | I often use Face Analysis in my workflows but we never actually talked about how it actually works. Here all you need to know. Remember to upgrade the extensions, these are all new features!
Check my Discord for the workflows, they are all free for everybody to use.
00:00 Intro 00:21 Face Embeds Distance 01:47 Similarity Metrics 07:27 Image Random Transform 08:29 Face Detailer 12:21 Face Warp 14:48 Face AlignHow to use PuLID in ComfyUILatent Vision2024-05-13 | In this video I'm going through some basic PuLID usage and also comparing it to other face models. If you have it already installed remember to upgrade the extension!
00:00 Intro 00:31 Basic Usage 02:41 Improve image with face analysis 05:59 Face detailer 11:16 Advanced node 13:35 Style transfer and attention masking 16:10 Comparing face models 16:35 Comparison PuLID 17:02 Comparison FaceID 17:52 Comparison PhotoMaker 18:06 Comparison FaceID Potrair Unnorm 18:32 Comparison InstantIDAnimation with weight scheduling and IPAdapterLatent Vision2024-04-30 | About time we talked about animations again! I just released new nodes IPAdapter and the Essential that make scheduling IPAdapter, Prompt and controlnet very easy and efficient.
00:00 Intro 01:10 Prep the keyframes 04:04 Scheduled weights 13:55 Scheduled prompt ipadapter and controlnetAll new Attention Masking nodesLatent Vision2024-04-21 | I just pushed an update to simplify attention masking and regional prompting with IPAdapter.
Be sure to upgrade the IPAdapter and the ComfyUI Essential to get access to all the new features.
00:00 Intro 00:15 Basic Attention Masking 02:30 Regional Conditioning 08:00 Prevent Embeds BleedingBecome a Style Transfer Master with ComfyUI and IPAdapterLatent Vision2024-04-15 | This time we are going to: - Play with coloring books - Turn a tiger into ice - Apply a different style to an existing image
00:00 Intro 00:26 Style Transfer 03:05 Composition Transfer 04:56 Style and Composition 07:42 Improve the composition 08:40 OutroBuild Your Own ComfyUI APP!Latent Vision2024-03-14 | This time we are getting our hands dirty into code! I wanted to show you how easy it is to build custom web applications with ComfyUI and absolutely no knowledge of python. Let me know if you'd like more of this kind of content!
The ComfyUI options to run the comfy from any device in your network are: --listen 0.0.0.0 --enable-cors-header '*'
00:00 Comfy Dungeon Introduction 02:14 Build your own ComfyUI App 15:24 Add CFGRescale 18:05 OutroVariations with noise injection KSampler (in pills)Latent Vision2024-03-04 | This is a kind of experiment I'm doing... I try to pack my videos with a lot of information and sometimes it might feel overwhelming. I was thinking maybe you'd also appreciate shorter videos dedicated to just one concept or even just one node. Please let me know what you think and if you'd like more of this kind of videos.
00:00 Intro 00:34 Base workflow 02:32 Face Analysis 03:30 Augment with IPAdapter 06:00 Style with IPAdapter 08:04 Posing the character 10:31 Multi-ID 12:33 Styling the background 13:59 InstandID AdvancedComfyUI: Advanced understanding Part 2Latent Vision2024-02-18 | This is Part 2 of my basics series. Last time we learned how to set the conditioning to the whole scene, time to see how to make localized changes.
I'm also talking about LCM, Math Nodes and other big and small tricks! As always do let me know what you think and if I should keep releasing "basics" tutorials or you prefer more advanced stuff.
00:00 Intro 00:30 Area Conditioning 02:20 Math Nodes 04:31 Latent Upscale 06:56 External Photo Editing 08:53 Conditioning Mask 10:13 GLIGEN 12:04 LCM 13:57 Inpainting Latent Mask 16:56 Inpainting Models 18:37 Models merging 19:59 Outpainting 23:17 Removing the latent mask 24:40 OutroMaking Trading Cards with ComfyUILatent Vision2024-02-07 | This time we are playing some card games! This tutorial will show you how to generate very different elements and mix them together into a nice composition.
00:00 Intro 00:53 The Frame 06:22 The Main Character 07:45 The Text Area 11:07 The Symbol 14:36 The Final Composition 16:40 Writing Text 18:42 Bonus StageThrowing data to your face (models)!Latent Vision2024-01-24 | I ran hours of benchmarks to try to establish what is the best IPAdapter face model and this is not a subjective selection: this video is backed by Science :)
00:00 Intro 00:17 Models benchmarks 04:53 Ideal Workflow 06:24 Changing hair color 08:22 Upscaling 10:15 Multiple reference images 11:41 FaceID Portrait 15:46 Two people workflow 19:37 OutroComfyUI: Advanced Understanding (Part 1)Latent Vision2024-01-12 | This time we are going back to basics! This is a deep dive into how ComfyUI and Stable Diffusion works. It's more than a basic tutorial, I try to explain how Comfy works underneath.
Please note that this is a test video, let me know what you think and it you'd like me to publish more videos like this together with my usual content.
00:00 Intro 00:28 The Checkpoint 04:19 The Clip 04:50 The KSampler 06:43 Samplers and Schedulers 11:03 Conditioning 12:21 Conditioning Concat 13:08 Conditioning Combine 14:08 Conditioning Average 15:42 Timestepping 17:08 Texture inversion and Word weighting 18:02 Unet Clip VAE loaders 19:51 OutroFaceID Take 2! Even more face models! (IPAdapter+ComfyUI)Latent Vision2023-12-31 | Since my last video Tancent Lab released two mode Face models and I had to change the structure of the IPAdapter nodes so I though I'd give you a quick update.
This is also the first time I don't use a BGM... the music helps to bring "everything together" and hide some of my bad English... but I understand that could be annoying for some, please let me know what you think.
00:00 Intro 00:42 Basic FaceID 02:50 FaceID with FullFace and PlusFace 04:27 FaceID Plus 05:26 FaceID Plus v2 07:26 Templates and Groups 09:55 Face Models Comparison 12:24 OutroFaceID: new IPAdapter modelLatent Vision2023-12-23 | New FaceID model released! Time to see how it works and how it performs.
00:00 Intro 01:14 Basic FaceID 04:23 Enhancing FaceID 08:37 Comparing all face models 10:54 Reality Check 11:47 StableZero123 with FaceID 14:10 Animated StableZero123 17:48 Outro
*** Background music *** - "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License - "Manace" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) - "Last Stop" Synthwave by Karl Casey @ White Bat AudioJellyfish Ballerina Animation with AnimateDiffLatent Vision2023-12-16 | This time I'm building an animation from the ground up, starting from the text prompt, adding controlnets and IPAdapter. There are a couple of advanced techniques that you might find interesting: 1) tiling the IPAdapter reference, 2) hiding part of an original image to the controlnet
00:00 Intro 00:37 Transition Mask Generator 02:57 Basic AnimateDiff Workflow 04:25 Adding ControlNets 06:37 Tiling IPAdapter 11:14 Masking the Background 14:13 Style IPAdapter 15:58 Increasing the Quality 17:47 Increasing the Frame Count 19:31 Outro 20:15 Bonus Stage
*** Background music *** -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License - "Manace" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) -- "Last Stop" Synthwave by Karl Casey @ White Bat AudioImage stability and repeatability (ComfyUI + IPAdapter)Latent Vision2023-12-08 | This time it's all about stability and repeatability! I'm generating a character and an outfit and trying to reuse the same elements in multiple settings, poses and facial expression.
00:00 Intro 00:22 Building the face 05:35 IPAdapter face model 07:55 The body 10:53 Merging face and body 16:51 Women always get the best armors 17:15 Modern outfit 18:06 Outro
*** Background music *** -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License -- "Last Stop" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) -- "CyberPunk City" by Peritune (peritune.com) -- "White Gold" by Karl Casey @ White Bat AudioAnimations with IPAdapter and ComfyUILatent Vision2023-11-30 | I just updated the IPAdapter extension for ComfyUI with all features to make better animations! Let's have a look!
*** Background music *** - "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License - "Manace" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) - "Last Stop" Synthwave by Karl Casey @ White Bat AudioInfinite Variations with ComfyUILatent Vision2023-11-25 | This time I'm exploring ways to generate variations over a reference image using only text prompts and noise (without control net). The topic is rather basic but I'm exploring some advanced techniques.
*** Background music *** - "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License - "Nightmare City" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) - "Manace" Synthwave by Karl Casey @ White Bat AudioAttention Masking with IPAdapter and ComfyUILatent Vision2023-11-14 | Exciting new feature for the IPAdapter extesion: it's now possible to mask part of the composition to affect only a certain area... And you can use multiple masks for a perfect result. This and much more directly from the developer of the ComfyUI Extension.
🎵 Background Music -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License -- "White Gold" by Karl Casey @ White Bat Audio (whitebataudio.com) -- "CyberPunk City" by Peritune (peritune.com)Upscale from pixels to real lifeLatent Vision2023-11-11 | This time I'm having fun upscaling old retrogame pixel art to live action characters in ComfyUI. It's basically an overview over various upscaling techniques, Tile ControlNet and a little of prompt engineering. Hope you find it useful!
00:00 Intro 00:25 Prompting 02:40 Tile ControlNet 04:30 Latent vs Pixel Upscalers 06:36 Latent Upscale 08:07 Model based Latent Upscale 09:43 Image Upscale (pixel space) 10:59 Image Upscale with Model 12:44 Upscale with ControlNet 15:15 Wrap up with another example 20:13 Conclusions
🎵 Background Music -- CyberPunk City by Peritune (peritune.com/blog/2020/05/22/cyberpunk_city) -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License -- Last Stop Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com)From real to anime (with IPAdapter and ComfyUI)Latent Vision2023-11-05 | Easy and effective way to apply the IPAdater models to get a "realism" slider from cartoonish to ultra-realistic with everything in between. We talk about prompt engineering, upscaling and of course IPAdapter.
🎵 Background Music -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License -- "Nightmare City" Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) -- "Menace" Synthwave by Karl Casey @ White Bat AudioComfyUI IPAdapter Advanced FeaturesLatent Vision2023-10-22 | This is a followup to my previous video that was covering the basics. If you are new to IPAdapter I suggest you to check my other video first.
🎵 Background Music -- "Part A" by Alexander Nakarada (serpentsoundstudios.com) Licensed under Creative Commons BY Attribution 4.0 License -- Last Stop Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com) -- Menace Synthwave by Karl Casey @ White Bat Audio (whitebataudio.com)How to use IPAdapter models in ComfyUILatent Vision2023-09-30 | Everything you need to know about using the IPAdapter models in ComfyUI directly from the developer of the IPAdapter ComfyUI extension.