Flux Workflows: Updated Models, ControlNet & LoRa in ComfyUI

Поділитися
Вставка
  • Опубліковано 1 лис 2024

КОМЕНТАРІ • 111

  • @SebAnt
    @SebAnt 2 місяці тому +6

    Thanks for testing the cutting edge models and keeping us up to date. 🙏🏽

  • @pixelzen007
    @pixelzen007 2 місяці тому +1

    Excellent work mate! Clean, concise and right to the point. I rarely comment on youtube videos. But you deserve a comment. Well done and keep up!

  • @Gabriecielo
    @Gabriecielo 2 місяці тому

    Well explained and caught up all latest info as usual, thanks a lot!

  • @tveerco6800
    @tveerco6800 2 місяці тому

    Just want I needed, thanks so much!

  • @marshallodom1388
    @marshallodom1388 Місяць тому

    Awesome video, thanks!
    I got a error about multiplying a floating point number (time_factor) by a nonetype (zero for time) which does not compute. Python 3.10 allows you to code Int | none but should be coded as Union[A, B] : return which will return actual numbers.
    Simply adding a ConditioningSetTimestepRange of course didn't work.

    • @CodeCraftersCorner
      @CodeCraftersCorner  Місяць тому

      Thank you for the comment! I haven’t encountered this error myself, but if I find a solution, I’ll be sure to post it here.

  • @Radarhacke
    @Radarhacke 2 місяці тому +2

    Thank You very Much!

  • @СанжарАльжанов-г4ь
    @СанжарАльжанов-г4ь 2 місяці тому +1

    Nice Job! 👍

  • @Archalternative
    @Archalternative 2 місяці тому

    Excellent video:) Bravo.

  • @rubenrodenascebrian3855
    @rubenrodenascebrian3855 2 місяці тому +1

    Great video! Could you upload your workflows? Thank you very much.

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Thank you! In the description of the video, there is a section "Resources". Click on the updated workflows link. You can then drag either the dev or schnell image into ComfyUI to load the workflow.

  • @YTbannedme-g8x
    @YTbannedme-g8x 2 місяці тому +2

    Im using a guidance scale of 2.5 for realism. I find that the default 3.5 scale makes the skin look like it has a plastic HDR sheen to the skin. The higher the scale the less realism. But like you said, a lower scale sacrifices prompt adherence.

    • @bgtubber
      @bgtubber 2 місяці тому

      Yes, there's a sacrifice there. I'm thinking of a way to compensate for this. So my idea is, what if you leave guidance scale at 3.5 and use the DynamicThreasholdingFull node with mimic_scale set to 2? Have you tried this?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Thanks for sharing, both of you! I will give these numbers a try.

  • @zdwork
    @zdwork 2 місяці тому

    Could you please write a tutorial on using PULID with FLUX🙏🙏🙏

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Hello, currently PuLID is only for SDXL models. Once we get support for FLUX, I will do one.

  • @mehmetalirende
    @mehmetalirende 2 місяці тому

    can you please explain if we have 2 loras, and they are different persons, how can we implement, it without effecting each other. lets think like a couple picture?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Hello, maybe try with a lora stack node. There are plenty in the manager. You will have to test out which settings will work. It still early with the flux and loras.

  • @nomorejustice
    @nomorejustice 2 місяці тому

    keep up the good work man! is the flux dev version work for low vram with 512 size?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Thank you! Yes, I am using it with 4GB of VRAM generating images at 1024 size.

  • @PyruxNetworks
    @PyruxNetworks 2 місяці тому +1

    you don't need to download again if you already have fp16 models. you can use flux model merger node and create fp8 checkpoint.

  • @GamingLegend-uq3on
    @GamingLegend-uq3on 2 місяці тому

    Hello sir,
    Your videos are great and very informative. Sir i have a question and after reading in your bio that you are a python guy i'm pretty sure you will help me out. so i want to migrate my python installation from my c drive to another drive can you please help me out how can i do that without breaking everything like my comfyui installed in my system locally?
    Waiting for your comment

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Thank you! If you only want to move ComfyUI, then you can move then entire ComfyUI folder if you have the portable version. In case you installed ComfyUI manually, I think you will have to reinstall it on the other drive.

    • @GamingLegend-uq3on
      @GamingLegend-uq3on 2 місяці тому

      @@CodeCraftersCorner i will give you my situation idea why I want this, i want to move python to another drive not cmfyui. So when I run comfyui on my laptop the problem is I have python in my c drive and when i load models and my c drive start doing reads and writes it gets hot and with it being hot my wifi card is right below it and heat causes my wifi to shut down itself randomly. So I'm wondering if I move python to another drive and that other drive get into the use then I don't have this problem as far as I am thinking. Let me know if it is possible .

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      @GamingLegend-uq3on In this case, the problem might still persist. Python itself doesn't generate much heat, but image generation and heavy processing can cause your CPU/GPU to heat up. Moving Python to another drive won't change the fact that ComfyUI will still use your CPU/GPU for processing, which might lead to the same heating issue. But if you want to give it a try, you will have to reinstall python in the new drive and change in python path in the environment path.

  • @sunlightlove1
    @sunlightlove1 2 місяці тому

    thanks again man

  • @DanielSchweinert
    @DanielSchweinert 2 місяці тому +1

    Change the values in the ModelSamplingFlux for Max Shift 0.5 and Base Shift 0.3 this will give you also more photorealism. And of course you can also lower FluxGuidance 1.8 - 2.3

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Thanks for sharing, I will give it a try!

    • @chiptaylor1124
      @chiptaylor1124 2 місяці тому

      I tried these settings, and it just made the image blurry? Any hep greatly appreciated. Thank you

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      @chiptaylor1124 If it helps, I am using the default values with more emphasis on the prompt.

    • @chiptaylor1124
      @chiptaylor1124 2 місяці тому

      @@CodeCraftersCorner Thank you!

  • @satishpillaigamedev
    @satishpillaigamedev 2 місяці тому

    Hey nice , What about the control net

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Hello. for now, there seems to be more issues with the controlnet than good results. You can monitor the progress by going into the description, under the resources section, there is a link controlnet issues.

  • @carterknudsen525
    @carterknudsen525 2 місяці тому

    Great video -- thanks!
    I'm having an issue running this workflow; I get this error: "ERROR: Could not detect model type of: C:\comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\models\checkpoints\flux1-dev-fp8.safetensors"
    Any idea how to fix this?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Thank you. For the model error, you will need to download it and place it in the folder ComfyUI > models > checkpoints.

  • @Maeve472
    @Maeve472 2 місяці тому

    What extension you are using to preview nodes?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      It's a ComfyUI update. I made a video on it and explain how to set it up here: ua-cam.com/video/8an9mkpDS2o/v-deo.html

  • @Decay3333
    @Decay3333 2 місяці тому

    can you use it with schnelle?

  • @Atenea-u4x
    @Atenea-u4x 2 місяці тому

    Hello,
    can you tell me why my flux shchnell is a .sft? I put it in models/unet and I dont understand why my schnell is sft and yours is not, also it will be different from the dev1.

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Hello, the .sft only has the UNET component. To get the safetensors one, go into the description of the video and click on the "Updated workflows" link. This will take you to a post. The first line where it says "checkpoint for the Flux dev here", click on the "here" link and download the safetensors file. Place them in the models > checkpoints folder.

    • @Atenea-u4x
      @Atenea-u4x 2 місяці тому

      @@CodeCraftersCorner thank you for the detailed answer, please tell me what means I only have the unet component? I got the files from a workflow for flux the first days of release and I dont know very well what im doing. I really appreciate to understand a bit more.
      Thank you !

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      @@Atenea-u4x There's two ways of using the Flux models. The sft files you have require a specific workflow. I made a video explaining about them. I think it would be easier to follow the video than explaining it with text. You can watch it here: ua-cam.com/video/OaS9hFD_xz8/v-deo.html

  • @trizais
    @trizais 2 місяці тому

    what is that ide that you use with the icons on the left? can you tell me please where I can download it?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +2

      It is the Edge browser. I changed the setting to show tabs on the left side instead of at the top.

  • @renzocheesman6844
    @renzocheesman6844 2 місяці тому

    can i simply use a custom made Lora inside comfyui with flux? im a noob

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Yes, add your lora to ComfyUI > models > loras folder.

  • @pixelzen007
    @pixelzen007 2 місяці тому

    The new models that are half in size and supposed to be faster is taking much longer than the original 22 GB version (dual clip workflow). The original version takes 2 mins per image in my PC but the new supposedly faster version takes about 15-20 mins. Something is really off here. But not sure what. My comfyui is uptodate. I used the same workflow you showed in the video. Why do you think this is?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Hello, not sure! Anyone else with this issue?

    • @juliana.2120
      @juliana.2120 Місяць тому

      if you mean the GGUF versions, its the same for me and i dont understand why. i'm on mac m3, hbu? i was wondering if its a mac+GGUF issue

  • @NeonXXP
    @NeonXXP 2 місяці тому

    Is this only working on FP8? im using FP16 with a 3090 and its throwing errors that I don't understand

  • @catskingdom7619
    @catskingdom7619 2 місяці тому

    Can you please make a video on how to make a professional profile pic using flux. You may replace the face from a professional ai image.

  • @lostinoc3528
    @lostinoc3528 27 днів тому

    When can we use more than 1 lora

  • @2PeteShakur
    @2PeteShakur 2 місяці тому +5

    nice, but bro pls use night mode, those white site scenes are blinding me! ;)

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +2

      Thanks for letting me know! My system automatically switches to light mode during the day and dark mode at night, so I didn’t realize this. I'll make sure to adjust it in future videos.

  • @muhammadidrees9481
    @muhammadidrees9481 2 місяці тому

    The workflow is not working showing me error "failed to fetch". How to solve this problem

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Hello, you can try to update your ComfyUI. If you have the portable version, go into the updates folder and open the update_comfyui_and_dependencies.bat file. Once completed, start ComfyUI and try again. Updating through the Manager alone seems to not work well.

  • @voxyloids8723
    @voxyloids8723 2 місяці тому

    I have the same mice arrow color )

  • @chaitanyapatel-cj5cr
    @chaitanyapatel-cj5cr 2 місяці тому +1

    whats your pc specs?

  • @jonmichaelgalindo
    @jonmichaelgalindo 2 місяці тому

    There's a negative prompt workflow on Civitai now. 🙂

  • @BibhatsuKuiri
    @BibhatsuKuiri 2 місяці тому

    I don't know why but my generated image looks grainy. I am following the exact workflow that is given in the website.anyonefacing the same issue,

  • @Maeve472
    @Maeve472 2 місяці тому

    lora key not loaded?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      Hello, can you try this one: flux_RealismLora_converted_comfyui. There is a link in the description of the video.

  • @brianmolele7264
    @brianmolele7264 2 місяці тому

    still requires insane VRAM ?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Yes for fast generation. I am using GTX 1650 4GB VRAM and 32GB of RAM. It takes about 10 minutes with the schnell model. Dev model takes way too long though but both works.

  • @tveerco6800
    @tveerco6800 2 місяці тому

    I get a little more realistic image at denoise 0.9 instead of 1

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Interesting! Thanks for sharing. I will give this a try.

  • @KINGLIFERISM
    @KINGLIFERISM 2 місяці тому

    Anyone else got an error message when trying to use the controlnet?

    • @aiamonlylove
      @aiamonlylove 2 місяці тому

      AttributeError: 'NoneType' object has no attribute 'keys'

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Yes, it seems it is broken. They made a code branch separated from the main branch. It seems more experimental for developers for now. You can see the progress and how to get the controlnet branch from here: bit.ly/4cqA1dt

  • @mayorc
    @mayorc 2 місяці тому

    No way of finetuning yet?

  • @LouisGedo
    @LouisGedo 2 місяці тому

    Hi

  • @Ajaysingh-x5d4p
    @Ajaysingh-x5d4p 2 місяці тому

    i think flux is not available for commercial activity , Right ? and this is from a privet entity and we are training their model / debugging / being habitual without having free and stable future of development even don't have commercial rights, right? so our time is not valuable or just some ytubrs making money by spreading this?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому +1

      The flux schnell is available for commercial activity. The dev model is under non-commercial research purposes only. Fun fact, the output (generated images) from the dev model can be used independently for commercial purposes.

  • @Piotr_Sikora
    @Piotr_Sikora 2 місяці тому

    dev is better, but it can't be use commercial

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      While the model itself is strictly for non-commercial research only, the images you generate with it are free to use for commercial purposes.

  • @nannan3347
    @nannan3347 2 місяці тому

    So many bad Flux tutorials on UA-cam. Why not just include a link to the ComfyUI workflow in the description?

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Thanks for watching! You may have missed it but there is a link in the video description under the [RESOURCES] section that says "Updated Workflows".

  • @Kartman-w6q
    @Kartman-w6q 2 місяці тому

    probably the main criticism on flux as of now is that it can't do realistic images very well. I tend to disagree, but I've got mixed results. anyway, judging on your screens it looks like that lora is either undertrained, or just garbage

    • @2PeteShakur
      @2PeteShakur 2 місяці тому +1

      hehe give it a chance, its very impressive so far, miles better than the crud of sd3, good blooming riddance! XD

    • @CodeCraftersCorner
      @CodeCraftersCorner  2 місяці тому

      Yes, although it's not an all-in-one perfect model, flux is better than any previous models so far.

    • @reasonsreasonably
      @reasonsreasonably 2 місяці тому

      ​@CodeCraftersCorner "better" at text, and better at adhering to certain prompts, but simply can't do certain things that would seem basic. I don't want to go into it right now, but Flux is a good start but I'll take SDXL with all the tools we have until Flux has more lora and the like.

    • @AIImagePlaymates-r7h
      @AIImagePlaymates-r7h 2 місяці тому +1

      I disagree as well with those people, the images have come out looking very realistic. This is the most realistic that I've seen the images so far since I've started generating AI images. I can't see myself going back to anything outside of FLUX.

    • @2PeteShakur
      @2PeteShakur 2 місяці тому

      @@AIImagePlaymates-r7h definitely, images are awesome and when it comes to realism, i don't need to adjust any particular settings really, i just add more details to the prompt, it's great! :)

  • @tazztone
    @tazztone 2 місяці тому

    DoRa i read are better than LoRa. maybe a topic for a next video. cheers