Code Crafters Corner
Code Crafters Corner
  • 63
  • 281 888
SD 3.5 Large Model: What’s the Best Sampler and Settings?
Exploring Stable Diffusion 3.5 Large Model’s limits with samplers, schedulers, and optimal settings for stunning images.
In this video, we dive deep into the new Stable Diffusion 3.5 Large Model, testing various samplers, schedulers, CFG values, and step counts to see what settings produce the best results in ComfyUI. From finding the lowest step count for clear images to adjusting CFG for an ideal balance, each test unveils key insights that could enhance your AI image generation workflow. Tune in to see which settings bring out the best in SD 3.5!
If you found this video helpful, please give it a like and subscribe to the channel so you don't miss out on future tutorials. You can also support the channel by joining my Patreon or becoming a free member.
[SUPPORT THE CHANNEL]
Patreon: bit.ly/44js1Xx
PayPal: bit.ly/45lJsIg
[RESOURCES]
Previous video on SD3.5 Turbo: ua-cam.com/video/SHieZiDWTwo/v-deo.html
All images are here: github.com/SharCodin/UA-cam-Video-Archive
(Go into the Stable Diffusion 3.5 Large test results folder.)
[SOCIAL MEDIA]
UA-cam Channel: bit.ly/4b0o8dQ
Twitter X: bit.ly/3ReP9D3
[BUSINESS INQUIRIES]
For professional inquiries and collaborations, please contact me via email:
Email: CodeCraftersCorner@gmail.com
(Use this email for business-related matters only)
[LAST TEN VIDEOS]
Stable Diffusion 3.5 Turbo: ua-cam.com/video/SHieZiDWTwo/v-deo.html
Stable Diffusion 3.5: ua-cam.com/video/3-pQqJJgqy8/v-deo.html
ComfyUI Flow Frontend: ua-cam.com/video/-OCwHBur0FM/v-deo.html
ComfyUI updates: ua-cam.com/video/P4-Nxy5bkUw/v-deo.html
Local Pyramid Flow installation: ua-cam.com/video/KPs_TsFuQ1I/v-deo.html
Pyramid Flow Project: ua-cam.com/video/3KAcyt4l1iY/v-deo.html
Flux.1 Dev upscaler: ua-cam.com/video/c-xUonw1r9s/v-deo.html
Alimama Controlnet Inpaint: ua-cam.com/video/0XJrjDnGp8w/v-deo.html
SD 1.5 and SDXL LoRAs in Flux: ua-cam.com/video/03nGYqj4nOM/v-deo.html
AWPortrait - Fine-tuned Flux: ua-cam.com/video/McL5W9BJ7S8/v-deo.html
ComfyUI Updates: ua-cam.com/video/4ELwfccXkHw/v-deo.html
Accessing Localhost Application from online services: ua-cam.com/video/ztfR6qVXjeQ/v-deo.html
Flux Prompting: ua-cam.com/video/phtGr4mZ-vU/v-deo.html
[TIMESTAMPS]
00:00 Introduction
00:30 Testing Samplers and Schedulers
05:21 Number of steps
06:57 CFG
10:25 Model Sampling
11:20 Conclusion
Thank you for watching!
[TAGS]
comfyui, Code Crafters Corner, CodeCraftersCorner, Image Editing, Creative Generation, AI Image Processing, Image Stylization, Workflow Automation, Comfy UI, Stable Diffusion,
Stable Diffusion 3.5, ComfyUI, AI image generation, samplers, schedulers, CFG settings, step count, SD 3.5 testing, best AI image settings, model sampling, large model
[HASHTAGS]
#StableDiffusion #ComfyUI #CodeCraftersCorner #ImageEditing #CreativeGeneration #aiprocessing #imagestylization
#StableDiffusion #ComfyUI #AIArt #ImageGeneration #Samplers #AIExperimentation
Переглядів: 1 109

Відео

I tested all possible combination for Stable Diffusion 3.5 Turbo
Переглядів 2,2 тис.21 годину тому
If you found this video helpful, please give it a like and subscribe to the channel so you don't miss out on future tutorials. You can also support the channel by joining my Patreon or becoming a free member. [SUPPORT THE CHANNEL] Patreon: bit.ly/44js1Xx PayPal: bit.ly/45lJsIg [RESOURCES] All images are here: github.com/SharCodin/UA-cam-Video-Archive (Go into the Stable Diffusion 3.5 Turbo test...
Stable Diffusion 3.5 in ComfyUI: Day 1 Support - Installation and Workflow
Переглядів 3 тис.День тому
Learn how to set up Stable Diffusion 3.5 in ComfyUI with day-one support. In this video, we dive into the brand-new Stable Diffusion 3.5 model and how it integrates seamlessly with ComfyUI on day one! I'll show you step-by-step how to set it up, where to place the models, and how you can get it running on your local machine. We’ll explore the differences between the large and turbo models, thei...
New ComfyUI Front-End: Easier Than You Think? Demo & Installation Guide - Flow
Переглядів 2,6 тис.День тому
Discover a new, easier way to use ComfyUI with this alternative front-end interface - Flow. In this video, I explore an exciting alternative front-end for ComfyUI that simplifies image generation without losing any of the backend power. I'll take you through a quick demo, show you how to install it, and give you my thoughts on the pros and cons of this new interface. If you found this video hel...
ComfyUI October 2024 Update: New Nodes, Samplers & A Major Workflow Change
Переглядів 4,9 тис.14 днів тому
Explore the latest ComfyUI updates with new features, nodes, and a workflow change you need to know about. Stay updated with the latest ComfyUI developments! In this video, we dive into the key updates from October 2024. Learn about the new alimama controlnet inpainting node, the integration of CFG samplers, and the introduction of the Laplace scheduler. We’ll also walk you through breaking wor...
Local ComfyUI Guide: Pyramid Flow for Text to Video Creation
Переглядів 1,9 тис.14 днів тому
ComfyUI and Pyramid Flow for dynamic video creation. In this tutorial, we take a deep dive into ComfyUI, specifically the Pyramid Flow wrapper. Learn how to optimize your VRAM usage, install custom nodes, and generate stunning videos by combining images in ComfyUI. From setting up the Pyramid Flow model to decoding samplers and previewing images, this step-by-step guide will walk you through th...
Exploring Pyramid Flow: Open-Source Text-to-Video Project!
Переглядів 67514 днів тому
Discover Pyramid Flow, the open-source future of text-to-video generation. In this video, I dive into an exciting new project called Pyramid Flow, a cutting-edge text-to-video generation tool. It utilizes autoregressive video generation based on flow matching, and it's fully open-source! I’ll walk you through its capabilities, show real examples, and discuss its limitations, including the licen...
Flux.1 Dev ControlNet Upscaler: Boost Image Resolution in ComfyUI
Переглядів 6 тис.Місяць тому
Master the Flux.1 Dev ControlNet Upscaler in ComfyUI to upscale images effortlessly. In this video, we dive into the Flux.1 Dev ControlNet Upscaler, a powerful model designed for enhancing low-resolution images. I'll walk you through the process of upscaling images from noisy, blurry resolutions to much higher clarity using this model. You’ll also learn how to set up the workflow in ComfyUI for...
Alimama Flux ControlNet In-Painting with ComfyUI: Step-by-Step Guide
Переглядів 3,1 тис.Місяць тому
Learn how to master Flux ControlNet in-painting with ComfyUI in this complete step-by-step guide. In this video, I walk you through how to use the Flux ControlNet in-painting model, designed for the Flux 0.1 dev model. Released by Alimama's creative team, this powerful tool offers an innovative way to refine your in-painting workflows in ComfyUI. I'll show you how to update your ComfyUI, instal...
How to Use SD 1.5 & SDXL LoRas with the Flux Model | Step-by-Step Workflow Guide
Переглядів 7 тис.Місяць тому
Learn how to integrate SD 1.5 & SDXL LoRas into a Flux workflow for stunning image generation. In this video, I show you how to integrate SD 1.5 and SDXL LoRas into a Flux workflow using ComfyUI. From setting up your basic Flux workflow to using LoRas designed for SD models, I guide you through each step. Whether you're into generating high-quality 3D animation styles or fine-tuning your denois...
Exploring the AWPortray-FL: A Fine-Tuned Flux 0.1 Model for Fashion Photography in ComfyUI
Переглядів 3,9 тис.Місяць тому
In this video, we take a deep dive into the AWPortray-FL model, a fine-tuned version of the Flux 0.1 Dev model by Shakker Labs, designed specifically for fashion photography. Learn how this model, trained on high-quality photos, enhances skin texture and composition. We'll also cover comparisons with the original Flux Dev model, testing in ComfyUI, and tips for generating top-tier fashion portr...
ComfyUI Update: New Frontend Features & Flux Model Support
Переглядів 5 тис.2 місяці тому
Discover the new ComfyUI frontend features and Flux model support in this in-depth guide. In this video, we dive into the latest updates for ComfyUI, focusing on the new frontend enhancements and the much-anticipated support for the Flux model. Learn how to update your ComfyUI, explore the new menu and workflow management, and see what's changed with the latest version. Whether you're using the...
How to Access Your Localhost Application from Any Device - Easy Setup!
Переглядів 7662 місяці тому
In this tutorial, I’ll show you how to make your local development environment accessible from the internet in just a few easy steps! Whether you’re using Flask, Gradio, or any other framework, you’ll learn how to create a public URL using services like Google Colab, ngrok, and online GPU services like vast.ai. Perfect for those working on machine learning projects or web apps! If you found thi...
Improve your flux image generation with prompts, explained!
Переглядів 7 тис.2 місяці тому
In this video, I explained about how to properly do flux prompting to get consistent and good images. If you found this video helpful, please give it a like and subscribe to the channel so you don't miss out on future tutorials. You can also support the channel by joining my Patreon or becoming a free member. [SUPPORT THE CHANNEL] Patreon: bit.ly/44js1Xx PayPal: bit.ly/45lJsIg [RESOURCES] Workf...
The evolution of AI Image Generation from Stable Diffusion to Flux
Переглядів 9542 місяці тому
Two Years, Infinite Possibilities: Celebrating two years of revolutionary advancements in AI image generation with Stable Diffusion. In this video, we take a deep dive into the incredible journey of Stable Diffusion over the past two years. From the early days of SD 1.1 to the groundbreaking releases of SDXL and the latest Flux Schnell, the AI image generation landscape has evolved at a lightni...
Flux IPAdapter: Comprehensive Guide with LoRA & ControlNet Integration
Переглядів 5 тис.2 місяці тому
Flux IPAdapter: Comprehensive Guide with LoRA & ControlNet Integration
ComfyUI Big Update & Flux Workflow Guide: Breaking Changes Explained!
Переглядів 7 тис.2 місяці тому
ComfyUI Big Update & Flux Workflow Guide: Breaking Changes Explained!
Flux ControlNet Integration & New LoRAs Explained
Переглядів 10 тис.2 місяці тому
Flux ControlNet Integration & New LoRAs Explained
Flux Workflows: Updated Models, ControlNet & LoRa in ComfyUI
Переглядів 20 тис.2 місяці тому
Flux Workflows: Updated Models, ControlNet & LoRa in ComfyUI
Flux Model Update: Smaller, Faster, and Just as Powerful!
Переглядів 11 тис.2 місяці тому
Flux Model Update: Smaller, Faster, and Just as Powerful!
ComfyUI's Big Update: New Frontend Coming August 15, 2024
Переглядів 6 тис.2 місяці тому
ComfyUI's Big Update: New Frontend Coming August 15, 2024
Exploring Image-to-Image with Flux 0.1 Schnell: A Deep Dive into the Latest Update in ComfyUI!
Переглядів 7 тис.2 місяці тому
Exploring Image-to-Image with Flux 0.1 Schnell: A Deep Dive into the Latest Update in ComfyUI!
Exploring Flux.1 Schnell: Revolutionary AI Model for Image Generation
Переглядів 6 тис.3 місяці тому
Exploring Flux.1 Schnell: Revolutionary AI Model for Image Generation
Comparing Face Generation Workflows: Photomaker V1, V2, IPAdapter FaceID and InstantID
Переглядів 1,9 тис.3 місяці тому
Comparing Face Generation Workflows: Photomaker V1, V2, IPAdapter FaceID and InstantID
PhotoMaker V2 in ComfyUI: Full Guide and Updated Workflow
Переглядів 4,3 тис.3 місяці тому
PhotoMaker V2 in ComfyUI: Full Guide and Updated Workflow
Photomaker V2 Review: Enhanced Face Generation for Stable Diffusion
Переглядів 2,8 тис.3 місяці тому
Photomaker V2 Review: Enhanced Face Generation for Stable Diffusion
Undo Your Art with Paints-Undo: Step-by-Step Guide
Переглядів 1,3 тис.3 місяці тому
Undo Your Art with Paints-Undo: Step-by-Step Guide
LivePortrait: Add emotions to your still images by animating the face in ComfyUI - Stable Diffusion
Переглядів 1,7 тис.3 місяці тому
LivePortrait: Add emotions to your still images by animating the face in ComfyUI - Stable Diffusion
ComfyUI PuLID: Installation and Workflow made EASY!!!
Переглядів 6 тис.3 місяці тому
ComfyUI PuLID: Installation and Workflow made EASY!!!
ComfyUI Updates: Stable Diffusion 3, Stable Audio and AuraFlow
Переглядів 1,8 тис.3 місяці тому
ComfyUI Updates: Stable Diffusion 3, Stable Audio and AuraFlow

КОМЕНТАРІ

  • @zengrath
    @zengrath 11 годин тому

    Thanks for the video. by default this plugin is dissapointing how is mangles the eyes, and on very full portrait close up it still looks painted. but combining this with reactor and reactor restore seems to be a good combo.

  • @RandMpinkFilms
    @RandMpinkFilms 15 годин тому

    Fantastic video!! Super clear!! Thank you for this!

  • @elvismorellidigitalvisuala6211

    PulidInsightFaceLoader Error. I'm getting crazy

  • @jonnygudman1815
    @jonnygudman1815 День тому

    You makes a dam good Job with your explainigs.

  • @Larimuss
    @Larimuss 3 дні тому

    Can't believe I've never used flux text encode. Thanks. I'm curious what results it gets with controlnets and lora though. Do you put lora keywords in top style clip box? Also using a 4070ti man I feel ripped off in the vram for the big price tag in AUS. I'll have to see how long it takes mine to get as I feel like it's 60-120 seconds. Do you use low vram mode?

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Hello, yes, you will put any keywords in the top box. However, the workflow to use Flux model changes quite rapidly. If you are using the fp8 simplified version, then there will be only one clip text encode (normal default one, same as sd1.5, sdxl one). For vram, it defaults to normal vram mode.

  • @Famekraftscom
    @Famekraftscom 5 днів тому

    What about cartoon Disney and Pixar? Does it work for them?

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Yes, requires quite a bit of trial and error though. Will be better to get lora specific to the art style.

    • @Famekraftscom
      @Famekraftscom День тому

      @CodeCraftersCorner I managed to create. The quality is better than xl

  • @homebox7922
    @homebox7922 6 днів тому

    Thank you so much ...

  •  6 днів тому

    Again very useful, thank you! I was scratching my head as to which parameter would do what... What is your personal opinion? What did you deduce from the test, what parameters do you think gave the best picture?

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Thank you! For me personally, i am using these: sampler: euler, scheduler: sgm_uniform, steps: 20 for (finding the composition), 40 (final image), cfg: 4.5 - 5.5 to make the model follow the prompt.

  • @krakenunbound
    @krakenunbound 6 днів тому

    It would be nice that when you do these videos you would, at the end, flat out say what your favorite settings are for what kind of art. Just tell us what to use.

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Thanks for the feedback! For me personally, i am using these: sampler: euler, scheduler: sgm_uniform, steps: 20 for (finding the composition), 40 (final image), cfg: 4.5 - 5.5 to make the model follow the prompt.

  • @BaldrysLight
    @BaldrysLight 6 днів тому

    Thank you for making these videos! I was trying to learn ComfyUI and all the related functions. My brother was supposed to help me out and now he is nowhere to be seen. I appreciate the effort of posting these videos, I have a slow GPU and its hard to keep up at times. Please keep makng videos!

  • @pawelthe1606
    @pawelthe1606 7 днів тому

    For me best settings are: sampler-euler, scheduler-sgm_uniform, steps-40, cfg-5.5. Great for realism and art.

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Thanks for sharing. I do the same. for steps, I do 20 and check the composition and then 40 for the final output. CFG: from 4.5 - 5.5 depending on the complexity of the prompt.

  • @GreenAppelPie
    @GreenAppelPie 7 днів тому

    Not impressed. What is 3.5 supposed to offer?

    • @CodeCraftersCorner
      @CodeCraftersCorner День тому

      Hello is a diffusion based model. So we can expect same improvements as with sd1.5, sdxl models.

  • @francaleu7777
    @francaleu7777 7 днів тому

    could you explain what model sampling is?

    • @CodeCraftersCorner
      @CodeCraftersCorner 7 днів тому

      Hello, I'll try. The sampler dictates the noisy image will change to a detail one. The model sampling shift how this happens.

  • @devnull_
    @devnull_ 7 днів тому

    TBH, I stick with Euler and whatever scheduler seems to work. Unless one has time to generate like 20 images with each possible combination of samplers and schedulers, it is pretty hard to know how it affect the prompt you are trying to craft. Some combinations clearly work better for some concepts, but I wish there was less choices of samplers and schedulers (in some sense, of course options are nice), and better prompt understanding instead.

    • @CodeCraftersCorner
      @CodeCraftersCorner 7 днів тому

      I, too, share the same opinion. It took me nearly 6 hours (with breaks in between) to generate all these images, and it’s just not practical to keep generating so many when adjusting the prompt. Thanks for sharing your thoughts!

    • @devnull_
      @devnull_ 7 днів тому

      @@CodeCraftersCorner btw thanks for trying these out, I personally simply try to prompt things that didn't or did work with earlier models while swapping samplers and schedulers, so it is nice to see some sort of structured overview too.

  • @francaleu7777
    @francaleu7777 7 днів тому

    thank you!!

  • @jorgerodrigues8869
    @jorgerodrigues8869 7 днів тому

    Thanks! I like having all the sliders on the left. But I still need the nodes. There's a new extension, called "Comfy Controller" (cg-controller"), that lets us have both !

  • @skycladsquirrel
    @skycladsquirrel 7 днів тому

    If anyone is having issues, just copy and paste the error into Chat GPT it will walk you through how to fix anything with a step by step guide. Thank for the great video!

  • @ayeshanaikodi6764
    @ayeshanaikodi6764 7 днів тому

    Very helpful! Thank you!

  • @Distty
    @Distty 7 днів тому

    Thank you for the honest review. Long-time subscriber, like everyone else say you deserve more subscribers, good content.

  • @yct6956
    @yct6956 8 днів тому

    don't know which part has error, when i press queue prompt, python error

    • @CodeCraftersCorner
      @CodeCraftersCorner 8 днів тому

      Hello, usually the error message should be in the terminal (CMD). It will tell you if there is anything missing.

    • @yct6956
      @yct6956 7 днів тому

      @@CodeCraftersCorner python.exe has been quit the cmd only has `Using split attention in VAE` no error code left

  • @bluelantern5241
    @bluelantern5241 8 днів тому

    Can you use regular sdxl 1.0 checkpoints?

    • @CodeCraftersCorner
      @CodeCraftersCorner 8 днів тому

      Not for now. Pyramid Flow uses its own model.

    • @bluelantern5241
      @bluelantern5241 7 днів тому

      @@CodeCraftersCorner I'm getting added token errors. Also had to change the name of the config.json file because it couldn't find it until I changed the name. I'm assuming I'll get more errors but I'm stuck at the added tokens error

  • @King_Kendhammer
    @King_Kendhammer 8 днів тому

    I am new to SD and this was super helpful. Do you have any courses that teach Stable Diffusion?

    • @CodeCraftersCorner
      @CodeCraftersCorner 8 днів тому

      Thank you! No, not yet but you will find more videos on the channel about Stable Diffusion and ComfyUI.

  • @RogerFr7
    @RogerFr7 9 днів тому

    Thanks for sharing man! I think there is one similar, do you think you could test Visionatrix? Great Job keep going!

  •  9 днів тому

    This is again a very useful, interesting test! I personally would be more interested in the Large version, because it focuses on image quality rather than speed.

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      Thanks! Yes, I am doing the large version but it's taking longer

  • @zephilde
    @zephilde 9 днів тому

    Hi! Did you try the same with more steps or on non turbo model ?

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      Hello! Yes, I am doing the large version but it's taking longer. I will post the results once completed.

  • @pawelthe1606
    @pawelthe1606 9 днів тому

    For me the best settings tested for realism (portrait) are: Model Sampling SD3 shift on 2.00, steps on 4, cfg on 1,sampler - euler, scheduler-beta. Time for generation with amazing results about 15 seconds.

  • @PixelsVerwisselaar
    @PixelsVerwisselaar 9 днів тому

    Nice thanks 🙌

  • @brokenbizkit
    @brokenbizkit 9 днів тому

    is 18+ content possible with this version? asking for a friend.

  • @pika9985
    @pika9985 9 днів тому

    would you do the same test but for realistic picture result ? in a new video

    • @pawelthe1606
      @pawelthe1606 9 днів тому

      Try this settings: Model Sampling SD3 shift on 2.00, steps on 4, cfg on 1,sampler - euler, scheduler-beta. Time for generation with amazing results about 15 seconds.

    • @pika9985
      @pika9985 9 днів тому

      @@pawelthe1606 thanks and unfortunately now i'm able to use cpu interference , os either turbo sd35 or waiting for a similar lightning 4step lora , then i stuck at cfg 1 , so i ask about what best scheduler and sampler for realistic output

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      Yes, I planned to experiment with realistic pictures too.

    • @pedrogorilla483
      @pedrogorilla483 8 днів тому

      No, please do it in the same video 😜

  • @sudabadri7051
    @sudabadri7051 9 днів тому

    Amazing work mate

  • @CalladsEssence
    @CalladsEssence 9 днів тому

    Thank you Sharvin for this comparison!

  • @zoom1972idi
    @zoom1972idi 9 днів тому

    Отличное видео, спасибочки. Можно вашу схему для Comfy Ui?

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      Hello, yes. You can use the images from the GitHub repository (link in description). You can drag and drop the image onto ComfyUI to load the workflow.

  • @Kaoru8168
    @Kaoru8168 9 днів тому

    I use the deis sampler for everything it works for 3.5 too

  • @sharinel
    @sharinel 10 днів тому

    Why not just use SwarmUI? It's a front end done by the Comfy guys anyway

  • @aegisgfx
    @aegisgfx 10 днів тому

    I hope the irony is not lost on anyone that a program called comfy UI had to have a different UI installed on top of it to make it useable

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      The attached UI isn't necessary, as the native ComfyUI is designed for creativity and experimentation. While it might seem challenging at first, everyone starts somewhere and gets more comfortable over time.

  • @SenseMusicGroup
    @SenseMusicGroup 10 днів тому

    New model is absolute trash Flux is 10x better

    • @gkiss2030
      @gkiss2030 10 днів тому

      Looks so...is the new SD model suitable for T-shirt graphics?

    • @CodeCraftersCorner
      @CodeCraftersCorner 9 днів тому

      Will do a comparison!

  • @flyingdogsoft
    @flyingdogsoft 10 днів тому

    Lol 😂 something much better is coming soon

  • @pawelthe1606
    @pawelthe1606 10 днів тому

    SD3.5 its amazing for art generative pictures not really for realistic in my opinion. Combination of picture with art styles for example Van Gogh or Andy Warhol or Japanese ink painting style gives amazing results. Almost endless possibilities of mixing different styles with your ideas.

  • @gordonbarbay750
    @gordonbarbay750 10 днів тому

    Thanks for the video! In the example large model workflow, the negative prompt is followed by several conditioning nodes before heading in to the KSampler, whereas the positive prompt goes directly to the KSampler. If the negative prompt is ignored, do you know why it has all those conditioning prompts attached to it?

  • @ronbere
    @ronbere 10 днів тому

    I miss the old nodes search so much

  • @WhySoBroke
    @WhySoBroke 10 днів тому

    Super!! Many thanks amigo! ❤️🇲🇽❤️

  • @yngeneer
    @yngeneer 10 днів тому

    Hello and thanks for the news. Is it really necessary to zero out the negative? connecting it directly into ksampler seems works fine...

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Thank for sharing! I will try.

    • @yngeneer
      @yngeneer 10 днів тому

      @@CodeCraftersCorner I mean... it is there for some reason for sure. I just don't know why...

  • @badashphilosophy9533
    @badashphilosophy9533 10 днів тому

    im using pinokio to install comfyui, in 1 click. hoping i dont run into any issues trying to install comfyui manager this way but this will be very helpful if i do

    • @badashphilosophy9533
      @badashphilosophy9533 10 днів тому

      no way, you're even explaining that to. damn, talk about comprehensive. but cant install manager through it? u didnt mention.

    • @badashphilosophy9533
      @badashphilosophy9533 10 днів тому

      i had to come back because Pinokia looks like its going to install comfyui manager automatically yay. if so Pinokio seems like the best tool ever for non coders or people who dont want to follow many links and go through a million steps, however, i have hit a snag with my graphics cards last and latest driver still being to old. it gave me the link to get the pytorch script to install referencing something called cuda. it didnt work with the basic install either. i guess pinokio automatically installs the gpu version :O damn, i might have to do it the first way you explained after all, i guess at least it would have installed all dependancies so it should be quicker now

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Yes, pinokio is one click installer but if the maintainers do not update the installation file, there's not much we can do. It's good to know how to install manually in that case.

  • @badashphilosophy9533
    @badashphilosophy9533 10 днів тому

    best explanation ever

    • @badashphilosophy9533
      @badashphilosophy9533 10 днів тому

      i love your arrows and boxes to direct attention, may i ask how u do that incase i one day make tutorial videos for helpful things like you

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Thank you!

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Oh, I used a windows utility tool called zoomit. It's free, you can get it from microsoft website.

    • @badashphilosophy9533
      @badashphilosophy9533 10 днів тому

      @@CodeCraftersCorner wow thanks. that will be so handy. thanks for the timely response

  • @MarkOakleyComics
    @MarkOakleyComics 10 днів тому

    After having gone to the trouble of learning ComfyUI and its many complicated parts, I would be extremely frustrated if I had to work with a pared down GUI like that. It seems like a step backwards. But that's where the rest of the world is headed, I suspect. Thank-goodness I got in early to learn about LLMs! Knowing the nitty-gritty is power.

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Great! This is a custom node made by an independent developer. I do not think it will become part of ComfyUI Core just yet. So, your knowledge of ComfyUI will still be useful.

  • @gamingreef2115
    @gamingreef2115 10 днів тому

    I am getting an error

  • @GrantLylick
    @GrantLylick 10 днів тому

    Just use forge then.

    • @StrikerTVFang
      @StrikerTVFang 10 днів тому

      Does Forge have workflows you can search through like Flow? I like different 1 click workflows without dealing with nodes if possible. If Forge has that, then perfect.

    • @GrantLylick
      @GrantLylick 10 днів тому

      @@StrikerTVFang I'm not kicking this video at all, it just looks like Forge to me.

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Thanks for sharing your thoughts! Yes, Forge has its own advantage while this is still ComfyUI.

    • @StrikerTVFang
      @StrikerTVFang 10 днів тому

      @@GrantLylick huh? No I was genuinely asking a question because I was thinking about using Forge lol

    • @GrantLylick
      @GrantLylick 9 днів тому

      @@StrikerTVFang I have both installed. Forge is pretty good.

  • @urieldeveaud
    @urieldeveaud 10 днів тому

    nice video... but huuumm, not convinced about this UI art the moment.. i like nodes! note: you can always drop your "queue toolbar" into the topbar ;)

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Thanks for sharing your thoughts! Yes, for people who like to be creative and tinker, the nodes are better. Yes, the queue panel can be collapsed. I actually made a video on the UI explaining the different elements. It can be found on the channel called: October 2024 ComfyUI updates.

  • @001mcv
    @001mcv 10 днів тому

    Thanks for another excellent and informative video!

  • @shuntera
    @shuntera 10 днів тому

    Hmmm, I ran the default large workflow and got this error, don't think it is due to memory: Requested to load AutoencodingEngine Loading 1 new model loaded completely 0.0 319.7467155456543 True D:\ComfyUI_windows_portable\ComfyUI odes.py:1506: RuntimeWarning: invalid value encountered in cast img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8)) Prompt executed in 146.87 seconds

    • @pawelthe1606
      @pawelthe1606 10 днів тому

      Maybe try to update comfy and see what happen. Make sure you got proper diffusers for large model also

    • @CodeCraftersCorner
      @CodeCraftersCorner 10 днів тому

      Try to update you ComfyUI through the terminal again. This implementation is part of the ComfyUI Core, so if you have enough memory, it should work. Also, you can try to redownload the checkpoints in case one got corrupted.