IPAdapter v2: all the new features! Latent Vision 2024-03-25 | 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.IPAdapter Extension: github.com/cubiq/ComfyUI_IPAdapter_plusSponsor the development of my extensions: paypal.me/matt3oDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:28 Unified Loader02:30 FaceID Models04:05 IPAdapter Advanced04:49 Weight Types05:56 Noise07:10 Merging Embeds11:55 Batch Nodes13:09 IPadapter Tiled14:47 Outro
Flux: all samplers, schedulers, guidance, shift tested! Latent Vision 2024-09-11 | I generated thousands of images with all combinations of schedulers, samplers, guidance, shift, steps and prompts... This is what I've learned.Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro01:19 Flux sampler with parameters05:06 Steps to converge09:14 Samplers and Schedulers13:41 Guidance16:09 Base and Max Shift19:36 Attention Seeker23:41 Outro
Math and conditions to build complex workflows Latent Vision 2024-08-27 | In this pill we are going to talk about Math, conditions, execution blockers and how I used them to build the Latent Upscaler.You can find the Flux dev upscaler here: gist.github.com/cubiq/73287231cff1e9ce7e90933ec74c2350The best way to stay up-to-date with all the workflows is on my completely open and welcoming Discord server. Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro00:26 Math Conditions02:56 Advanced Math 06:06 Triggers07:10 Latent Upscaler
Deep dive into the Flux Latent Vision 2024-08-15 | 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.zipComfyAnonymous' examples and models: comfyanonymous.github.io/ComfyUI_examples/fluxDiscord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro03:46 Basic workflow07:15 Prompt trouble with Art Styles09:59 Sampler Flux with Parameters15:37 Prompting20:41 Anime bias22:08 Noise injection24:20 Image to Image26:04 Outro
Best cuts from July 22nd Stream! Latent Vision 2024-07-24 | 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!Workflows: https://f.latent.vision/download/stream_20240722.zipDiscord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 ClipVision Enhancer04:00 How the enhancer work10:35 Enhance Ratio16:47 Difference with Tiled IPAdapter18:38 Rebuilding the workflow31:14 The Tile node34:02 Image2Video35:08 Sponsorship and open source37:00 Kolors IPAdapter43:28 Precise Composition49:52 Face segmentator56:34 Face segmentator with AnimateDiff59:38 Experimenting with the Mad Scientist1:03:10 Inspirenet Remove Background
Updates! ClipVision Enhancer, Kolors, Precise Composition and more! Latent Vision 2024-07-22 | A streamlined version of this video is available here: youtu.be/RnfyYWQ8oM8It has been a busy couple of weeks. I have updates for IPAdapter, the Essentials and Face Analysis. Let's talk about it!Workflows: https://f.latent.vision/download/stream_20240722.zipDiscord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq
ComfyUI Advanced Understanding Part 3 Latent Vision 2024-07-07 | Third installment of the Basics series. This time we are going to talk about ControlNet and Upscaling.It takes a lot more time to make the "basics" videos compared to my standard content so I really appreciate your feedback!Workflow: https://f.latent.vision/download/upscale_tiled.zipDiscord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro00:49 It's just noise03:40 ControlNet Canny08:56 Tidy the mess10:33 ControlNet OpenPose11:50 OpenPose with full body14:09 ControlNet Tile15:29 Simple Upscale18:11 Noise injection22:18 Upscale with tiling30:28 Upscale with model33:55 Outro
Advanced Style transfer with the Mad Scientist node Latent Vision 2024-06-24 | 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.Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro00:23 Style Transfer Precise02:03 Mad Scientist Node05:35 Advanced Blocks Tweaking07:27 CosXL Edit
Dissecting SD3 Latent Vision 2024-06-19 | How does SD3 work? Is it any good? No drama, no politics, only the technical side of things.The SD3 Negative node is part of the Comfy Essentials: github.com/cubiq/ComfyUI_essentialsFree SD3 generations at OpenArt: openart.ai/create?ai_model=stable-diffusion-3-sd3Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq00:00 Intro00:35 Default workflow05:46 Testing the negatives08:44 Lying in the grass12:40 Prompt adhesion15:19 Noise16:30 High resolutions17:28 Control Nets18:41 License
Higher quality images by prompting individual UNet blocks Latent Vision 2024-06-07 | 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.Extension repository: github.com/cubiq/prompt_injectionDiscord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiq
About AI, Art, Ethics and the environment Latent Vision 2024-06-02 | 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.What do you think?Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiqTED Talk by Sasha Luccioni: ted.com/talks/sasha_luccioni_ai_is_dangerous_but_not_for_the_reasons_you_think
How to use Face Analysis to improve your workflows Latent Vision 2024-05-24 | 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.Discord server: discord.com/invite/W2DhHkcjgnGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiqThe Face Analysis tool: github.com/cubiq/ComfyUI_FaceAnalysisThe Image Random Transform is part of the Essentials: github.com/cubiq/ComfyUI_essentials00:00 Intro00:21 Face Embeds Distance01:47 Similarity Metrics07:27 Image Random Transform08:29 Face Detailer12:21 Face Warp14:48 Face Align
How to use PuLID in ComfyUI Latent Vision 2024-05-13 | 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!PuLID ComfyUI extention: github.com/cubiq/PuLID_ComfyUIFace Analysis node: github.com/cubiq/ComfyUI_FaceAnalysisGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiqMy Discord server: discord.com/invite/W2DhHkcjgnWorkflows: https://f.latent.vision/download/pulid.zip00:00 Intro00:31 Basic Usage02:41 Improve image with face analysis05:59 Face detailer11:16 Advanced node13:35 Style transfer and attention masking16:10 Comparing face models16:35 Comparison PuLID17:02 Comparison FaceID17:52 Comparison PhotoMaker18:06 Comparison FaceID Potrair Unnorm18:32 Comparison InstantID
Animation with weight scheduling and IPAdapter Latent Vision 2024-04-30 | 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.Workflows: https://f.latent.vision/download/scheduled_weights.zipGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oTwitter: twitter.com/cubiqMy Discord server: discord.com/invite/W2DhHkcjgnBanodoco Discord server: discord.com/invite/8Wx9dFu5tPFor the LCM model you use either the beta one: huggingface.co/wangfuyun/AnimateLCM/blob/5e54afbbe191f00b8a701f76770ade4fb14685dc/sd15_t2v_beta.ckptor the final version: huggingface.co/wangfuyun/AnimateLCM/blob/main/AnimateLCM_sd15_t2v.ckpt00:00 Intro01:10 Prep the keyframes04:04 Scheduled weights13:55 Scheduled prompt ipadapter and controlnet
All new Attention Masking nodes Latent Vision 2024-04-21 | 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.The Essentials can be found here: github.com/cubiq/ComfyUI_essentialsDownload the workflow: https://f.latent.vision/download/new_attention_masking.zipGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:15 Basic Attention Masking02:30 Regional Conditioning08:00 Prevent Embeds Bleeding
Become a Style Transfer Master with ComfyUI and IPAdapter Latent Vision 2024-04-15 | This time we are going to:- Play with coloring books- Turn a tiger into ice- Apply a different style to an existing imageGithub sponsorship: github.com/sponsors/cubiqSupport with paypal: paypal.me/matt3oDiscord server: discord.com/invite/W2DhHkcjgnAll the workflows can be downloaded here no strings attached: https://f.latent.vision/download/style_transfer.zipThe SDXL lineart controlnet: huggingface.co/TencentARC/t2i-adapter-lineart-sdxl-1.000:00 Intro00:16 Sketch to Image08:52 Replace objects and materials12:41 Apply style to image17:02 Negative image conditioning
Style and Composition with IPAdapter and ComfyUI Latent Vision 2024-04-04 | IPAdapter Extension: github.com/cubiq/ComfyUI_IPAdapter_plusGithub sponsorship: github.com/sponsors/cubiqPaypal: paypal.me/matt3oDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:26 Style Transfer03:05 Composition Transfer04:56 Style and Composition07:42 Improve the composition08:40 Outro
Build Your Own ComfyUI APP! Latent Vision 2024-03-14 | 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!Comfy Dungeon: github.com/cubiq/Comfy_DungeonThe FastGen extension can be downloaded from here: https://f.latent.vision/download/fastgen.zipDiscord server: discord.com/invite/W2DhHkcjgnThe 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 Introduction02:14 Build your own ComfyUI App15:24 Add CFGRescale18:05 Outro
Variations with noise injection KSampler (in pills) Latent Vision 2024-03-04 | 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.Discord server: discord.com/invite/W2DhHkcjgnComplete video about image variations: youtube.com/watch?v=Ev44xkbnbeQComfyUI Essentials: github.com/cubiq/ComfyUI_essentialsBlenderNeko's noise injection nodes: github.com/BlenderNeko/ComfyUI_Noise
InstantID: Everything you need to know Latent Vision 2024-02-24 | InstantID is a style transfer tool targeted to portraits. It's incredibly easy to create a composition in specific style. In this video I'm showing you how to improve the likeliness, how to make a scene with multiple people and much more!InstantID Extension: github.com/cubiq/ComfyUI_InstantIDFace Analysis Extension: github.com/cubiq/ComfyUI_FaceAnalysisGeneric Workflows: github.com/cubiq/ComfyUI_InstantID/tree/main/examplesWorkflows in this video: https://f.latent.vision/download/instantid.zipDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:34 Base workflow02:32 Face Analysis03:30 Augment with IPAdapter06:00 Style with IPAdapter08:04 Posing the character10:31 Multi-ID12:33 Styling the background13:59 InstandID Advanced
ComfyUI: Advanced understanding Part 2 Latent Vision 2024-02-18 | 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.Discord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:30 Area Conditioning02:20 Math Nodes04:31 Latent Upscale06:56 External Photo Editing08:53 Conditioning Mask10:13 GLIGEN12:04 LCM13:57 Inpainting Latent Mask16:56 Inpainting Models18:37 Models merging19:59 Outpainting23:17 Removing the latent mask24:40 Outro
Making Trading Cards with ComfyUI Latent Vision 2024-02-07 | 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.Workflows: https://f.latent.vision/download/trading_card.zipDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:53 The Frame06:22 The Main Character07:45 The Text Area11:07 The Symbol14:36 The Final Composition16:40 Writing Text18:42 Bonus Stage
Throwing data to your face (models)! Latent Vision 2024-01-24 | 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 :)Workflows: https://f.latent.vision/download/face_science.zipDiscord server: discord.com/invite/W2DhHkcjgnMarco's ComfyUI channel (in German): @ALatentPlace 00:00 Intro00:17 Models benchmarks04:53 Ideal Workflow06:24 Changing hair color08:22 Upscaling10:15 Multiple reference images11:41 FaceID Portrait15:46 Two people workflow19:37 Outro
ComfyUI: Advanced Understanding (Part 1) Latent Vision 2024-01-12 | 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.Debug node is part of the comfyui essentials: github.com/cubiq/ComfyUI_essentialsDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro00:28 The Checkpoint04:19 The Clip04:50 The KSampler06:43 Samplers and Schedulers11:03 Conditioning12:21 Conditioning Concat13:08 Conditioning Combine14:08 Conditioning Average15:42 Timestepping17:08 Texture inversion and Word weighting18:02 Unet Clip VAE loaders19:51 Outro
FaceID Take 2! Even more face models! (IPAdapter+ComfyUI) Latent Vision 2023-12-31 | 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.Comparison workflow: https://f.latent.vision/download/face_models_comparison.zipIPAdapter Plus Extension: github.com/cubiq/ComfyUI_IPAdapter_plusDiscord server: discord.com/invite/W2DhHkcjgnThis 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 Intro00:42 Basic FaceID02:50 FaceID with FullFace and PlusFace04:27 FaceID Plus05:26 FaceID Plus v207:26 Templates and Groups09:55 Face Models Comparison12:24 Outro
FaceID: new IPAdapter model Latent Vision 2023-12-23 | New FaceID model released! Time to see how it works and how it performs.Workflows: https://f.latent.vision/download/faceid.zipMotion controlnet: huggingface.co/crishhh/animatediff_controlnet/tree/mainIPAdapter Plus Extension: github.com/cubiq/ComfyUI_IPAdapter_plusDiscord server: discord.com/invite/W2DhHkcjgn00:00 Intro01:14 Basic FaceID04:23 Enhancing FaceID08:37 Comparing all face models10:54 Reality Check11:47 StableZero123 with FaceID14:10 Animated StableZero12317:48 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 Audio
Jellyfish Ballerina Animation with AnimateDiff Latent Vision 2023-12-16 | 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 controlnetDiscord server: discord.com/invite/W2DhHkcjgn*** Workflow ***Workflow: https://f.latent.vision/download/jellyfish_ballerina.zipThe original ballerina video: pexels.com/video/person-woman-girl-steps-499042700:00 Intro00:37 Transition Mask Generator02:57 Basic AnimateDiff Workflow04:25 Adding ControlNets06:37 Tiling IPAdapter11:14 Masking the Background14:13 Style IPAdapter15:58 Increasing the Quality17:47 Increasing the Frame Count19:31 Outro20:15 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 Audio
Image stability and repeatability (ComfyUI + IPAdapter) Latent Vision 2023-12-08 | 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.Workflow and all images: https://f.latent.vision/download/character_stability.zipDiscord server: discord.com/invite/W2DhHkcjgnIPAdapter extension: github.com/cubiq/ComfyUI_IPAdapter_plusComfyUI essentials: github.com/cubiq/ComfyUI_essentials@ALatentPlace 00:00 Intro00:22 Building the face05:35 IPAdapter face model07:55 The body10:53 Merging face and body16:51 Women always get the best armors17:15 Modern outfit18:06 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 Audio
Animations with IPAdapter and ComfyUI Latent Vision 2023-11-30 | I just updated the IPAdapter extension for ComfyUI with all features to make better animations! Let's have a look!OpenArt Contest: contest.openart.aiIPAdapter Extension: github.com/cubiq/ComfyUI_IPAdapter_plusAnimateDiff Extension: github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved00:00 Intro00:09 Animated Masks04:21 Logo Animation08:48 32-Frames11:39 Animated Reference Images15:19 Contest and Conclusion*** Workflows ***Download the masks from: cdn.matt3o.com/uploads/files/masks.zipLogo Animation: pastebin.com/9GbLTxVs4 Reference Images Animation: pastebin.com/JCcbciykDragon Lady: pastebin.com/ncFybRfE*** 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 Audio
Infinite Variations with ComfyUI Latent Vision 2023-11-25 | 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.*** Nodes ***IPAdapter Plus: github.com/cubiq/ComfyUI_IPAdapter_plusComfyUI Noise: github.com/BlenderNeko/ComfyUI_Noise*** Workflows ***Generic variations: pastebin.com/F95Mv3ZFUnsampler: pastebin.com/69PwaGdsNoise Injection: pastebin.com/LmSvMVF800:00 Intro00:26 SDXL width/height conditioning01:27 Light text conditioning03:13 Conditioning concat and combine06:17 Latent-2-Latent (with advanced KSampler)08:33 IPAdapter09:30 Unsampler13:59 Inject Noise15:48 Conclusions*** 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 Audio
Attention Masking with IPAdapter and ComfyUI Latent Vision 2023-11-14 | 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.You can find a few workflows in the examples directory of the ComfyUI_IPAdapter_Plus extension: github.com/cubiq/ComfyUI_IPAdapter_plusMore complex workflows (just download the json format):Masked conditioning: pastebin.com/DjYg6jMCComplex Masked conditioning: pastebin.com/PsD13EVKRGB Masking: pastebin.com/jBB9cAn200:00 Intro00:21 Weight types02:51 Attention Masking05:17 Multiple Masks08:57 Mask Conditioning10:48 Conclusions🎵 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 life Latent Vision 2023-11-11 | 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!The workflow: pastebin.com/jr8FEYTW00:00 Intro00:25 Prompting02:40 Tile ControlNet04:30 Latent vs Pixel Upscalers06:36 Latent Upscale08:07 Model based Latent Upscale09:43 Image Upscale (pixel space)10:59 Image Upscale with Model12:44 Upscale with ControlNet15:15 Wrap up with another example20:13 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 Vision 2023-11-05 | 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.IPAdapter: github.com/cubiq/ComfyUI_IPAdapter_plus/issuesCASharpening is part of: github.com/cubiq/ComfyUI_essentialsYou can download the workflow from here: pastebin.com/tppqDVUp00:00 Introduction00:24 Prompt Engineering03:34 IPAdapter07:16 Upscaling12:54 Sharpening14:25 SDXL17:24 AnimateDiff🎵 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 Audio
ComfyUI IPAdapter Advanced Features Latent Vision 2023-10-22 | 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.👉 Download the extension here: github.com/cubiq/ComfyUI_IPAdapter_plus👉 The crop node is part of my ComfyUI Essentials extension: github.com/cubiq/ComfyUI_essentials00:00 Introduction00:19 Weighting multiple images02:49 Prepping images03:58 IPAdapter models roundup05:37 Face model09:49 Timestepping12:17 AnimateDiff15:52 Conclusions🎵 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 ComfyUI Latent Vision 2023-09-30 | Everything you need to know about using the IPAdapter models in ComfyUI directly from the developer of the IPAdapter ComfyUI extension.👉 You can find the extension "ComfyUI_IPAdapter_plus" on github here: github.com/cubiq/ComfyUI_IPAdapter_plus00:00 Introduction01:33 Basic Workflow05:55 IPAdapter Plus Model07:32 Prepping Images09:16 Sending Multiple Images14:07 Face Model15:18 SDXL17:42 Img2Img19:10 Inpainting20:00 ControlNet21:40 Upscaling23:17 Saving embeds26:33 Conclusions🎵 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/blog/2020/05/22/cyberpunk_city)
