Tutorial Video : https://youtu.be/lgrM9xfh250
In this video, we explore Lumina Image 2.0 , the latest diffusion-based AI image generation model now natively integrated into ComfyUI. This powerful yet lightweight tool allows creators to generate high-quality images using simple text-to-image workflows, without the need for com...
2025-02-07 13:09:26 +0000 UTC View Post
Tutorial Video : https://youtu.be/2fgT35H_tuE
For Patreon Supporter, more advanced content : https://www.patreon.com/posts/workflow-flux-121648642
In this video, we’ll explore ACE Plus (ACE ++) , a new batch of Flux-based LoR...
2025-02-06 14:49:15 +0000 UTC View Post
This workflow are able to all 3 ACE Plus Lora Models setting in 1 workflow.
Follow the video tutorial, you will know how to switch mode for Local Edit, Subject and Portrait mode in this workflow. https://youtu.be/2fgT35H_tuE
Here are some examples in the meantime I was making.
Subject Transfer:
I was trying with fast motion in AI Video. :)
2025-02-05 04:26:14 +0000 UTC View Post
Related Tutorial : https://www.patreon.com/posts/121487379
Video : https://youtu.be/uJcQjhfwssM
Last time, we talked about Flow Edit V2V in Hunyuan Video https://youtu.be/TAdO9...
2025-02-04 13:48:42 +0000 UTC View Post
Video: https://youtu.be/uJcQjhfwssM
Additional Research and Content For Patreon Supporters: https://www.patreon.com/posts/121487753
In this video, we dive into the exciting world of Hanyuan Video , a powerful AI tool that allows you to trans...
2025-02-04 13:42:26 +0000 UTC View Post
Related Tutorial : https://www.patreon.com/posts/animate-x-ai-1-121408447
As I mentioned in the video, I have used AnimateDiff for refinement , and clean up the animation generated from Animate-X.
This workflow that I was using the AnimateDiff, and BBOX Segement to fix animation.
If you ...
2025-02-03 14:14:12 +0000 UTC View Post
Tutorial Video : https://youtu.be/hzYj_oHEByc
For Patreon Supporters Additional Content : https://www.patreon.com/posts/workflow-animate-121408839
In this video, we dive into Animate-X An AI Animation Framework, a cutting-ed...
2025-02-03 14:06:15 +0000 UTC View Post
I was checking out EasyAnimate latest update. The version 5.1 , it's interesting that they have change the model from Unet to Diffusion Transformer now. Well, looks like everyone are change to DiT, hopefully AnimateDiff will do as well.
https://github.com/aigc-apps/EasyAnimate/tree/main/comfyui
2025-01-31 20:45:00 +0000 UTC View Post
This is an updated version of ltx_v2v-flow_edit workflow.
In this workflow, I swtiched from Florenece 2 to DeepSeek AI Janus Pro for vision LM and using prompting for style transfer.
Video Tutorial : https://youtu.be/66XSSH6jThs
Other JanusPro workflow in tutorial : 2025-01-30 14:28:43 +0000 UTC View Post
Video: https://youtu.be/66XSSH6jThs
Unlock the full potential of DeepSeek AI's Janus Pro in ComfyUI with this comprehensive tutorial! In this video, we’ll guide you step-by-step on how to install and use the Janus Pro custom node for both image generation and image understanding tasks. Whether you’re a beginner or an adva...
2025-01-30 14:19:01 +0000 UTC View Post
Video : https://youtu.be/anfI6dGg8cE
In this video, we dive into DeepSeek AI, a leading Chinese AI company making waves with its advanced multi-model AI systems like Janus. Learn how DeepSeek's models, including the Janus Pro 7B, are pushing the boundaries of AI by combining text, image, and video understanding. From generati...
2025-01-29 13:00:11 +0000 UTC View Post
Video : https://youtu.be/hg9Ii3Od2wI
Discover how to bring old black-and-white family videos back to life with the power of AI! In this tutorial, we explore the SVFR (Unified Framework for Generalized Video Face Restoration), an open-source tool that uses Stable Video Diffusion (SVD) to enhance and colorize vintage footage. L...
2025-01-27 17:10:48 +0000 UTC View Post
Video : https://youtu.be/A8TGucJIGz4
Discover PixVerse 3.5, the @PixVerse_Official AI video generator that’s faster and more powerful than ever! In this video, we explore its Turbo mode, which generates high-quality videos in seconds, and its Image-to-Video feature for creating smooth, dynamic animations. Whether you're m...
2025-01-26 13:00:15 +0000 UTC View Post
Tutorial Video: https://youtu.be/wF5dk-QIAFQ
Discover PuLID Flux 2, the ultimate tool for face identification and character transformation in AI-generated images! In this video, we explore how to use PuLID Flux to seamlessly integrate faces into new images, creating natural-looking results without the awkward edges or pixelat...
2025-01-24 14:09:10 +0000 UTC View PostVideo : https://youtu.be/8bvjYYaHw3A
Discover the latest Kling AI 1.6 update and its powerful Elements feature! In this video, we explore how to create dynamic AI videos by mixing and matching multiple objects, characters, and backgrounds. Whether you're crafting cinematic scenes, e-commerce showcases, or creative sto...
2025-01-23 14:40:14 +0000 UTC View PostHey guys!
When you have try LTX, you know that this model need long form of video types of prompt in order to make some good motion, no matter what.
And if you use image caption for LTX img2vid , for the generated video, 90% possibility the character are stay still.
But this can be a benifit for creating talking avatar, becasue the character don't move too much.
So, I skip the part using LLM to convert image prompt to video prompt; I tested using caption from F...
2025-01-22 19:54:26 +0000 UTC View Post
Video: https://www.youtube.com/watch?v=VokxyQJw8NM
This is a ComfyUI custom node that I just made . This is the basic setup tutorial for this custom node, and how it can work with other custom node.
Unlock the power of Kokoro TTS with ComfyUI custom nodes! In this video, we dive into how to set up and use...
2025-01-22 16:15:40 +0000 UTC View Post
Video : https://youtu.be/HfhozzQD-WM
Workflows of 2 In the post, LTX with STG and LTX Flow Edit V2V (Freebies): https://www.patreon.com/posts/ltx-video-0-9-1-118605761?u...
2025-01-21 13:00:16 +0000 UTC View Post
I just uploaded it, will talk about this node in upcoming video 😉
https://github.com/benjiyaya/ComfyUI-KokoroTTS/
Video: https://youtu.be/KR-i-qUgAGE
In this video, we explore how this lightweight, open-source TTS model stacks up against industry leaders like ElevenLabs. Whether you're a content creator, developer, or AI enthusiast, this model offers a free and efficient way to generate high-quality speech from text.
Check it...
2025-01-20 13:00:14 +0000 UTC View PostHow is it? just a raw output video from ComfyUI, no upscale, no enhanced color.
I try using Kling AI gen a video, then brin to Comfyui.
I made a tts node (testing stage), combine with LatentSync for Lipsync.
Video : https://youtu.be/NtyhIcRR3NU
In this video, we dive into Nvidia Cosmo, the groundbreaking Text-to-World and Video-to-World diffusion models announced at CES 2025. Discover how to run Nvidia Cosmo in ComfyUI for Text-to-Video, Image-to-Video, and Video-to-Video workflows, and explore the future of AI video generation.<...
2025-01-16 14:50:51 +0000 UTC View Post
Video : https://youtu.be/fq95OLDVCdU
Hunyuan Video Image Prompt Node - Image To Guider
This is a ComfyUI custom node that I developed recently for Hunyuan Video.
Unlock the potential of Hunyuan Video with the Image Guider custom node! In this tutorial, I’ll show you how to use an image as a guid...
2025-01-14 13:00:13 +0000 UTC View Post
next video will talk about this one. in the meanwhile , you can play with it :)
https://github.com/benjiyaya/ComfyUI-HunyuanVideoImagesGuider
2025-01-13 22:23:04 +0000 UTC View PostReferring to the video tutorial : https://www.patreon.com/posts/119902314
Video: https://youtu.be/TAdO9ZPpzww
To Patreon Supporters:
I tidied up the flow edit workflow overall for something of what I think is working better.
... 2025-01-13 13:00:18 +0000 UTC View Post
Video Tutorial : https://youtu.be/TAdO9ZPpzww
Discover the power of Hunyuan Video with the Video-to-Video method using Flow Edit in ComfyUI! In this tutorial, we dive deep into how to transform video motions and styles seamlessly, creating stunning AI-generated videos with ease. Whether you're a beginner or an advanced user, ...
2025-01-13 13:00:14 +0000 UTC View Post
Hands up , here how I do it. I saw many people struggling on this part.
So, there are many other repo that have Triton.
Here's another one specific for Python 3.11 https://huggingface.co/madbuda/triton-windows-builds/blob/main/triton-2.1.0-cp311-cp311-w...
Hey everyone!
Hunyuan Video, like it, for Open Source AI Video. My current Go To AI model.
I got the Img2Vid Alike method, and here's the output : https://x.com/AIfutureBenji/status/1878054176116367436
I have been doing some research and use AI Coder copliet with me to create a custom no...
2025-01-11 21:53:38 +0000 UTC View Post
Video : https://youtu.be/wPiujsfr__Y
In this video, I’ll show you how to optimize your AI generation processing speed using Comfy WaveSpeed, a powerful set of custom nodes for ComfyUI. Whether you're working with image diffusion models like Flux or AI video models like Hunyuan Videos and LTX, this tool can significantly imp...
2025-01-10 14:30:01 +0000 UTC View Post