- Видео 25
- Просмотров 22 075
AI Jigyasa
Индия
Добавлен 18 май 2024
Hey there! I’m your AI jigyasa (AI Curiosity) host, and I’m here to make AI as friendly and approachable as your next-door neighbor. On this channel, we’ll unravel the mysteries of AI together, turning complex concepts into easy-peasy lessons. From perfecting prompts to creating visuals that wow, we’re on this creative adventure together. So, hit that subscribe button and let’s get started on this exciting journey into AI - it’s going to be a blast! 🚀💻❤️
Tools i use:
ComfyUI
Leonardo
Krea AI
Tools i use:
ComfyUI
Leonardo
Krea AI
Is FLUX REDUX really the BEST STYLE TRANSFER TOOL? #ai #flux #comfyui
In this video, I am going to tell you how you can use redux to generate images similar to your reference. This is an easy workflow because we are using a custom node that is already balancing between prompt and image. I am attaching the necessary files down below. Also if you want to see the full version of my videos. comment down below. I will go live occasionally and show you my experiments and we can create images together.
Content of this Video:
0:00 - Intro
4:16 - Redux Installation
6:09 - Workflow
12:26 - Another Example
16:16 - Outro
Please support me by buying me a coffee.
buymeacoffee.com/ai_jigyasa
Links 🔗
| Workflow - openart.ai/workflows/ai_jigyasa/flux-redux---best-style-transfer-tool/...
Content of this Video:
0:00 - Intro
4:16 - Redux Installation
6:09 - Workflow
12:26 - Another Example
16:16 - Outro
Please support me by buying me a coffee.
buymeacoffee.com/ai_jigyasa
Links 🔗
| Workflow - openart.ai/workflows/ai_jigyasa/flux-redux---best-style-transfer-tool/...
Просмотров: 339
Видео
GET Control of your images with Multi-Latent Composite in ComfyUI SDXL #ai #comfyui
Просмотров 143День назад
In this video, we dive deep into the power of the Multi-Latent Composite node in ComfyUI. Learn how to take control of your images, place characters or subjects exactly where you want, and elevate your creative projects to the next level! Links 🔗 Workflow - openart.ai/workflows/ai_jigyasa/multi_latent_composite-11/QKUMyHs65dUaBs2pt9pH MultiLatentComposite 1.1- github.com/Davemane42/ComfyUI_Dave...
I Discovered a FREE AI Tool That Converts Images to Videos Like Magic!
Просмотров 1,8 тыс.14 дней назад
Learn how to create awesome images and convert these images to videos for free. Grab the deal before it ends. 🧠 Did this spark your curiosity? Drop a 💡 in the comments! 🎨 Craving more AI visuals? Type "MoreAI" below! 👨🏫 Tutorial request? Leave "TeachMe" in the comments! 🔄 New AI animations every Friday. Don't miss out - hit subscribe! ✨ Your engagement fuels these creations. Like & share if yo...
1 Image Lora? Flux PuLID Makes It Happen! #ai #aialgorithms #flux #comfyui
Просмотров 2,6 тыс.21 день назад
Learn how to create consistent face images with just one source photo using Flux PuLID! This simple workflow leverages a unique '1 Image Lora' approach, allowing you to bypass the need for an IP adapter or face ID, making it perfect for seamless face-swaps. In this tutorial, I’ll show you how PuLID acts as a comprehensive workflow for generating consistent faces, will add upscaler and face deta...
Flux Workflow and 1-STEP Ultimate Upscale #ai #aialgorithms #flux #upscale #comfyui
Просмотров 1,5 тыс.Месяц назад
A simple workflow for Flux and 1 step upscale, THe flux is trained on very high quality images. so you will get outstanding images on the first go. go have fun with it. try different loras to get different results. find the required file links below- Workflow - drive.google.com/file/d/1bOkkKaavj1B2SbHYDcyAiMFemVSroJeu/view?usp=sharing Flux dev Model -huggingface.co/black-forest-labs/FLUX.1-dev/...
EXPAND YOUR IMAGE WITH THIS SIMPLE SDXL OUTPAINTING WORKFLOW
Просмотров 1032 месяца назад
Hi, this is my first video. I will use my Voice next time. I love the SDXL models and their capability to create outstanding Images. and Now we have SDXL inpainting. Dreamshaper XL lightning Inpainting model is great for correcting messed up details in an image or if you want to expand your horizon. The method is very easy to use. In this Outpainting Tutorial, I show you all the settings you ne...
I've tried several times to solve the problem following your suggestions, but I still haven't been able to fix it.
whats the error you are getting when running Pulid?
please check if you have installed the correct python based insightface.
This is the best tutorial... why they have too make it complex for simple things like this.. you are epic
@@ApexArtistX thank you. Wow.. wasn’t expecting this.
not free
it's free. hailuo or Minimax gives you free 100 credits every day. you can create 3 videos every day.
Sad you suddenly start to use AI voice. This takes away your channel's signature. Remember you made me laugh in one of your previous videos?
@@ohsocialmio3884 this video was sitting there in the corner. I thought why not upload it. It has information. Will be sharing same old videos with workflows.
@@aijigyasa ahh i see. Watched the Tyson match?
Nahh.. was working. The outcome was joke.
🤣🤣🤣🤣🤣🤣 14:51 "Wauwwwwwwwwwwww she is crispy now".
the final image its so blury
Increase the steps. Use Lora detailers; put blurry in negative when upscaling. that should fix it
"She looks exactly like her ... HMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMM" 😭😭😭😭😭😭🤣🤣🤣🤣🤣🤣
You loved the bit. I can tell by looking at your face. 🤣🤣🤣🤣🤣🤣
@@aijigyasa ah man you made me laugh
@ I am glad to know.
@@aijigyasa Yes, i have watched your video till the end. If you want and have the time can you make a flux workflow to create ultra realistic professional photos (not the plastic skin look with bad stare) based on uploaded photo with positive and negative prompts: 1. Consistency in character (currently i am working with fooocus and i have a female model i use in front of a black backdrop and when i want to use her i simply drop her photo and generate photos) 2. that fix the face that match the uploaded photo 3. next to normal generated photo an additional upscaled photo using the ComfyUI-Flowty-LDSR (currently one of the best for upscaling)
@ sure will look into it.
Does Not Work. I used your workflow and the image did not expand, only gave me gray padding on both sides.
Use inpainting checkpoint. i have given the link in the description. if it still doesn't work screenshot it and link it here.
i coulld not get it working on windows, but worked like a charm in ubuntu. I wonder if the upscaling nodes are necessary, considering default upscale value is 1.20. As it is it's quite slow, and upscaling just adds to the time
great. Upscaling is optional. I used it to refine some minor details; that's it.
Using your workflow and exact models/loras, I got this error: VAEDecodeTiled.decode() missing 1 required positional argument: 'overlap'
I think the problem is with Ultimate SD upscale. comfyui started rolling out vae decode tile with an overlap option. Wait for them to fix it. Meanwhile, you can turn off the Vae decode option at the bottom of Ultimate upscaler.. That should fix the problem.
it'd be funny 2-3 years from now yall get sued for using celebrities and that was part of the ai scam hahahahahahhahaha Oh man it'd be a laugh to watch all the people cry and act like they didnt know.... Pretty cool times we live in
@@Romeo615Videos this video is for educational purposes only. I used a celebrity face bcuz it’s easy to find high quality image. And it’s public. These images were used for all sorts of work memes or small ads. So i think we will be fine. But thanks for showing concern.
oh my god.... thx as always.
No worries. Keep Supporting.
@@aijigyasa its failing to build the insightface wheel no matter what I do. was reading somewhere the non-portable version does it without probs (maybe I have a path problem) will try tomm
@@MrDebranjandutta try installing insightface with your python version. Steps to Follow: Check the Python version in ComfyUI: 1. Go to the ~/comfyui/python_embedded folder and double-click on python.exe. Note the version of Python (e.g., 3.09, 3.10, 3.11, or 3.12). 2. Now open this link(in description) - github.com/Gourieff/Assets/tree/main/Insightface and download the same version as python. and move that file to comfyui folder where run_nvidia_gpu batch file exist. 3. now right click on it and copy as path. 4. right click anywhere in the folder and open in terminal and paste this command - .\python_embeded\python.exe -m pip install [paste path here] onnxruntime and hit enter. that's it. let me know if it fixes your problem.
Good stuff bro, subsd. Which gpu are you using btw? I have a poor mans 3060 can I use the full dev-fp8 model?. Like your goofball style. Keep at it
I also have a 3060 with 12gb Vram. You can run flux dev fp8 22gb variant. But it will take time and will slow down your pc movements too. Don’t even think about upscaling with FP8. I will recommend stick with the turbo lora’s or GGUF models. Or generate low res image with full fp8 and upscale with turbo with 8 step or GGUF. and thanks for the compliment 😬
After following your steps, I’m still getting the following error: (AttributeError: newbyteorder was removed from the ndarray class in NumPy 2.0. Use arr.view(arr.dtype.newbyteorder(order)) instead). If you have a solution for this, it would really help me move forward.
@@Bogdan_95 can you share the screenshot of your workflow? I want to see which node is giving you this error. Meanwhile try updating your comfyui.
@@Bogdan_95 try this fix also.. from folder - ComfyUI_windows_portable .\python_embeded\python.exe -m pip install numpy==1.26.3
@@aijigyasa Sure, I can do that. Where should I send the screenshot? Also, I have other workflows-would they break with the NumPy 2.0 update, or would they still work fine?
@@Bogdan_95 i don’t think its going to affects other workflows. Specially SdXl or 1.5 based workflows. This error occurs only in flux, specifically gguf loader or unet checkpoint loader. Have you tried the above methods btw? Here is a thread link. You will find a solution here. I hope this helps. No need for screenshot its a compatibility issue. github.com/city96/ComfyUI-GGUF/issues/7#issuecomment-2392951603
Doesn't look like 1-step upscale. Rather looks like upscaling two times with 20 step each
@@kallamamran sorry for the confusion: but by 1 step i mean just one node. You can’t do 1 step upscale bcuz there is no hyper turbo ultra flux lora right now. Will upload the fast upscaling method with this workflow. Stay tuned.
Dude. It was interesting to see your workflow. I smiled when flux only makes women. I hope you will do more complicated and interesting workflow. Goodluck and спасибо.
@@germanfa1770 thanks man. And yes will share more interesting workflows. Consider subscribing for future video. Appreciate you.
Where is the Workflow you said that you were going to put it below. I can't find it
Sorry. I forgot to put the link. please Check again, and you will find the workflow. Thanks for letting me know. Subscribe for more videos.
Weird as hell.
Looks good
Cool. i hate ai though.
doesn't look like Gojo. but the quality is good.
nice try
Thanks
images are nice
Thanks
i love the first 10 sec of it. it stretches after that.
I understand. It will get better. I am working on it. Thanks for the info.
This is not kakarot
looks like him.. Not exactly of ofcourse. But why do you think that?
Ai simply destroys everything 😢
Yes i agree. But its everywhere. We need to adapt. Thanks for being here though.
Tatti😢😮😅😊😅😮😢😂😂❤😂😢😮😅😅😂q❤🎉😢😅😊