AI Jigyasa
AI Jigyasa
  • Видео 25
  • Просмотров 22 075
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/...
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...

Комментарии

  • @pong4289pan
    @pong4289pan День назад

    I've tried several times to solve the problem following your suggestions, but I still haven't been able to fix it.

    • @aijigyasa
      @aijigyasa День назад

      whats the error you are getting when running Pulid?

    • @aijigyasa
      @aijigyasa День назад

      please check if you have installed the correct python based insightface.

  • @ApexArtistX
    @ApexArtistX 8 дней назад

    This is the best tutorial... why they have too make it complex for simple things like this.. you are epic

    • @aijigyasa
      @aijigyasa 7 дней назад

      @@ApexArtistX thank you. Wow.. wasn’t expecting this.

  • @waxcactu
    @waxcactu 13 дней назад

    not free

    • @aijigyasa
      @aijigyasa 13 дней назад

      it's free. hailuo or Minimax gives you free 100 credits every day. you can create 3 videos every day.

  • @ohsocialmio3884
    @ohsocialmio3884 15 дней назад

    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?

    • @aijigyasa
      @aijigyasa 15 дней назад

      @@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.

    • @ohsocialmio3884
      @ohsocialmio3884 15 дней назад

      @@aijigyasa ahh i see. Watched the Tyson match?

    • @aijigyasa
      @aijigyasa 14 дней назад

      Nahh.. was working. The outcome was joke.

  • @ohsocialmio3884
    @ohsocialmio3884 18 дней назад

    🤣🤣🤣🤣🤣🤣 14:51 "Wauwwwwwwwwwwww she is crispy now".

  • @jorgesharp
    @jorgesharp 19 дней назад

    the final image its so blury

    • @aijigyasa
      @aijigyasa 18 дней назад

      Increase the steps. Use Lora detailers; put blurry in negative when upscaling. that should fix it

  • @ohsocialmio3884
    @ohsocialmio3884 19 дней назад

    "She looks exactly like her ... HMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMMM" 😭😭😭😭😭😭🤣🤣🤣🤣🤣🤣

    • @aijigyasa
      @aijigyasa 19 дней назад

      You loved the bit. I can tell by looking at your face. 🤣🤣🤣🤣🤣🤣

    • @ohsocialmio3884
      @ohsocialmio3884 19 дней назад

      @@aijigyasa ah man you made me laugh

    • @aijigyasa
      @aijigyasa 19 дней назад

      @ I am glad to know.

    • @ohsocialmio3884
      @ohsocialmio3884 18 дней назад

      ​@@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)

    • @aijigyasa
      @aijigyasa 15 дней назад

      @ sure will look into it.

  • @baheth3elmy16
    @baheth3elmy16 20 дней назад

    Does Not Work. I used your workflow and the image did not expand, only gave me gray padding on both sides.

    • @aijigyasa
      @aijigyasa 20 дней назад

      Use inpainting checkpoint. i have given the link in the description. if it still doesn't work screenshot it and link it here.

  • @MrDebranjandutta
    @MrDebranjandutta 20 дней назад

    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

    • @aijigyasa
      @aijigyasa 20 дней назад

      great. Upscaling is optional. I used it to refine some minor details; that's it.

  • @baheth3elmy16
    @baheth3elmy16 21 день назад

    Using your workflow and exact models/loras, I got this error: VAEDecodeTiled.decode() missing 1 required positional argument: 'overlap'

    • @aijigyasa
      @aijigyasa 20 дней назад

      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.

  • @Romeo615Videos
    @Romeo615Videos 23 дня назад

    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

    • @aijigyasa
      @aijigyasa 22 дня назад

      @@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.

  • @ismgroov4094
    @ismgroov4094 23 дня назад

    oh my god.... thx as always.

    • @aijigyasa
      @aijigyasa 23 дня назад

      No worries. Keep Supporting.

    • @MrDebranjandutta
      @MrDebranjandutta 23 дня назад

      @@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

    • @aijigyasa
      @aijigyasa 22 дня назад

      @@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.

  • @MrDebranjandutta
    @MrDebranjandutta 24 дня назад

    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

    • @aijigyasa
      @aijigyasa 23 дня назад

      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 😬

  • @Bogdan_95
    @Bogdan_95 Месяц назад

    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.

    • @aijigyasa
      @aijigyasa Месяц назад

      @@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.

    • @aijigyasa
      @aijigyasa Месяц назад

      @@Bogdan_95 try this fix also.. from folder - ComfyUI_windows_portable .\python_embeded\python.exe -m pip install numpy==1.26.3

    • @Bogdan_95
      @Bogdan_95 Месяц назад

      @@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?

    • @aijigyasa
      @aijigyasa Месяц назад

      @@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

  • @kallamamran
    @kallamamran Месяц назад

    Doesn't look like 1-step upscale. Rather looks like upscaling two times with 20 step each

    • @aijigyasa
      @aijigyasa Месяц назад

      @@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.

  • @germanfa1770
    @germanfa1770 Месяц назад

    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.

    • @aijigyasa
      @aijigyasa Месяц назад

      @@germanfa1770 thanks man. And yes will share more interesting workflows. Consider subscribing for future video. Appreciate you.

  • @JuniorReveron
    @JuniorReveron Месяц назад

    Where is the Workflow you said that you were going to put it below. I can't find it

    • @aijigyasa
      @aijigyasa Месяц назад

      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.

  • @Thought_Fuel
    @Thought_Fuel 5 месяцев назад

    Weird as hell.

  • @Food_Fetish1
    @Food_Fetish1 5 месяцев назад

    Looks good

  • @Thought_Fuel
    @Thought_Fuel 5 месяцев назад

    Cool. i hate ai though.

  • @Food_Fetish1
    @Food_Fetish1 5 месяцев назад

    doesn't look like Gojo. but the quality is good.

  • @My-Gadgets-Zone
    @My-Gadgets-Zone 5 месяцев назад

    nice try

  • @My-Gadgets-Zone
    @My-Gadgets-Zone 5 месяцев назад

    images are nice

  • @amitkaprawan7998
    @amitkaprawan7998 5 месяцев назад

    i love the first 10 sec of it. it stretches after that.

    • @aijigyasa
      @aijigyasa 5 месяцев назад

      I understand. It will get better. I am working on it. Thanks for the info.

  • @KaranSingh-ze5nb
    @KaranSingh-ze5nb 5 месяцев назад

    This is not kakarot

    • @aijigyasa
      @aijigyasa 5 месяцев назад

      looks like him.. Not exactly of ofcourse. But why do you think that?

  • @PatrickHartwig
    @PatrickHartwig 5 месяцев назад

    Ai simply destroys everything 😢

    • @aijigyasa
      @aijigyasa 5 месяцев назад

      Yes i agree. But its everywhere. We need to adapt. Thanks for being here though.

  • @SatendraSharma-h5k
    @SatendraSharma-h5k 5 месяцев назад

    Tatti😢😮😅😊😅😮😢😂😂❤😂😢😮😅😅😂q❤🎉😢😅😊