Didn't know about the option to list the packages in ComfyUI but for me doesn't work. I follow those steps at 2:16 and get (ComfyUI Manager) and when I type pip doesn't seem like it feels it's installed. I installed ComfyUI thru a 64-bit installer file in Windows.
Hi, small products yes we can get great outputs.. Have you tried training a more complex product? Like a bike or a car? Thanks for sharing your learnings :)
My question is: If you can have consistant characters, how are consistant outfits achieved? Would it be though a LoRA (so eg you want her in a Space Marine Suit occasionally) wold you make the LoRA and plug it into the consistant AI workflow?
Yes you can use two LoRAs, one for your consistant character, and the other trained for your outfit. Just slightly reduce the strength of the outfit's LoRA.
I'll give this a shot. Comfy can do anything! I have both kohya and AI-toolkit installed on my RunPod Network storage. The learning curve for kohya, however, is steep. Thanks for the video. I saw your "handbag" video a few days ago and thought it was pretty professional. You should link that here so others can see it. Sure that Video cost you some major RunwayML credits to get your IG model moving as well as she did. Congraz on that video.
Yeh I've been using comfy locally for image gen. It's crazy what it can do. Been trying out lora on runpod. Fluxgym is really quick and easy but it would be good to use comfy then you just have workflows for everything 😂
i do the vediosays, but when training, it says a error"InitFluxLoRATraining module 'torch' has no attribute 'float8_e4m3fnuz'" could anybody told me how to solve this? thanks a lot
convert the sample prompts inputs converting to widget does physically not show up nor exist on my version of comfyui, neither does the popup window look the way it looks here. any idea why that is, and if there is a workaround for converting this to a widget? Google does no show any results when searching for this step, ..... see timestamp 8:58
Can u make a tutorial with a teenager / man lora model wearing a watch, training as product lora in comfy ui + flux? I love your content it is BRILLIANT!!
Does this require a separate 2nd install of comfyui? Or can this all,be done with the one I have running already. I saw some other tutorials where that was required or it would break your cui beyond repair. Can anyone verify?
guy could someone help me plese, why do i have this error: Warning: Missing Node Types When loading the graph, the following node types were not found: VisualizeLoss UploadToHuggingFace TrainDatasetAdd FluxTrainValidate FluxTrainValidationSettings FluxTrainSave OptimizerConfig FluxTrainEnd FluxTrainLoop FluxTrainModelSelect TrainDatasetGeneralConfig InitFluxLoRATraining No selected item Nodes that have failed to load will show as red on the graph.
@@Aiconomist oh ok...now my training is done and I had like 4:5 ratio but biggest side was 1024px. Well, I do some more testing anyways. My results really need an upscale but they do without the lora too. And I use the same ration and sizes for creation.
What happens if you train with images that are in 16:9 aspect ratio? Asking cus most everything I do is in 16:9 or 239 and don’t wanna have to outpaint everything
thanks for the tutorial, the images look really underwhelming. Many features are not matching on the original bag. Its really discouraging to see that type of results.
I have just rent a GPU and started looking for this kind of tutorial - THANK YOU!! I love how you slowly explain everything
You're very welcome!
Didn't know about the option to list the packages in ComfyUI but for me doesn't work. I follow those steps at 2:16 and get (ComfyUI Manager) and when I type pip doesn't seem like it feels it's installed. I installed ComfyUI thru a 64-bit installer file in Windows.
Thank you! an exceptionally good tutorial with basic information for a noob like me. you are a great teacher!
You're very welcome!
I had a lot or errors and missing nodes when loading the .json for the 1st time in ComfyUI
Looks fine, can we train face models on this one like is it working same as the fluxgym?
Hi, small products yes we can get great outputs.. Have you tried training a more complex product? Like a bike or a car? Thanks for sharing your learnings :)
My question is: If you can have consistant characters, how are consistant outfits achieved? Would it be though a LoRA (so eg you want her in a Space Marine Suit occasionally) wold you make the LoRA and plug it into the consistant AI workflow?
Yes you can use two LoRAs, one for your consistant character, and the other trained for your outfit. Just slightly reduce the strength of the outfit's LoRA.
I'll give this a shot. Comfy can do anything! I have both kohya and AI-toolkit installed on my RunPod Network storage. The learning curve for kohya, however, is steep. Thanks for the video. I saw your "handbag" video a few days ago and thought it was pretty professional. You should link that here so others can see it. Sure that Video cost you some major RunwayML credits to get your IG model moving as well as she did. Congraz on that video.
Thanks a lot. It's essentially the same thing. In that video, I used AI-Toolkit instead of this one and Kling instead of RunwayML.
@@Aiconomist is ai toolkit process in comfyui?
@@Aiconomist Okay, I did see the credits at the end of that video, Kling did a nice job.
Yeh I've been using comfy locally for image gen. It's crazy what it can do. Been trying out lora on runpod. Fluxgym is really quick and easy but it would be good to use comfy then you just have workflows for everything 😂
i do the vediosays, but when training, it says a error"InitFluxLoRATraining
module 'torch' has no attribute 'float8_e4m3fnuz'" could anybody told me how to solve this? thanks a lot
What video model or service did you use for the last section where they were animated?
Thanks for the content.
Good Thx. Please tell us about mixing LoRa in one stream (Mix LoRa)
convert the sample prompts inputs converting to widget does physically not show up nor exist on my version of comfyui, neither does the popup window look the way it looks here. any idea why that is, and if there is a workaround for converting this to a widget? Google does no show any results when searching for this step, ..... see timestamp 8:58
Is it possible to do this, not on Local. Something like Replit or Fal? Or does comfyUI off endpoints?
I tried the steps but with the missing nodes update in manager appears: " (IMPORT FAILED) ComfyUI Flux Trainer" ....can I solve it?
i have intel iris xe graphis , is it oky?
Can u make a tutorial with a teenager / man lora model wearing a watch, training as product lora in comfy ui + flux? I love your content it is BRILLIANT!!
If running Runpod, would you rather suggest using this method or the other method using AI-Toolkit in one of your videos?
"I don't recommend using the portable version" - how come?
Does this require a separate 2nd install of comfyui? Or can this all,be done with the one I have running already. I saw some other tutorials where that was required or it would break your cui beyond repair. Can anyone verify?
guy could someone help me plese, why do i have this error: Warning:
Missing Node Types
When loading the graph, the following node types were not found:
VisualizeLoss
UploadToHuggingFace
TrainDatasetAdd
FluxTrainValidate
FluxTrainValidationSettings
FluxTrainSave
OptimizerConfig
FluxTrainEnd
FluxTrainLoop
FluxTrainModelSelect
TrainDatasetGeneralConfig
InitFluxLoRATraining
No selected item
Nodes that have failed to load will show as red on the graph.
Same issue with me. Did you find any solution for it?
and where to get clip_i и text encoder, please!
Is it crucial that all training pics have the same size? And can they also be like 4:5?
Yes it's crucial, the images must be 1024x1024 pixels
@@Aiconomist oh ok...now my training is done and I had like 4:5 ratio but biggest side was 1024px. Well, I do some more testing anyways. My results really need an upscale but they do without the lora too. And I use the same ration and sizes for creation.
What happens if you train with images that are in 16:9 aspect ratio? Asking cus most everything I do is in 16:9 or 239 and don’t wanna have to outpaint everything
Were the results good enough with the 4:5 aspect ratio?
Can I use Runpod to use this flow?
Yes, you can follow the same steps
Does it work for people ? Like I have unfortunately a 8 gb card and I would like to make Lora of people
Of course you can but it is going to take longer.
are you available for custom script work?
Yes, you can find my email in the description box
How did you do the animation at the end?
Can someone tell me if this works on Mac?
just tried using the comfyUI manager, 'install from GitHub', I can see the nodes after updating to the new ComfyUI, but did not try it yet.
Can I try this in Google colab free version ?
Nice work 😊
how can i get course
You can find a direct link in the description box
i train my loras with it...good but i can't resume
This is useful contents.
But I don't think I'd actually use it for a product detail page.
The products need to match 100% accurately.
Just wait.. It will improving
Do you still think the same today?
thanks for the tutorial, the images look really underwhelming. Many features are not matching on the original bag. Its really discouraging to see that type of results.
Are the images better now?
ValueError, is not a directory ........
学一下
It's always a "Low VRAM" tutorial, for losers who are doing this thing on their MAC or cheap laptop
4090 so cool