ComfyUI I only use if it is really necessary, If you use Forge WebUI over Automatic1111 that is huge performance boost especially if you have Low VRAM. Personally I use Fooocus WebUI it is so practical image quality is better with foocus V2 expansion and styles, in painting very good and handy face swap image to image more than enough. If you have low VRAM ist is so fast and esay to use SDXL lightning models. Performance presets amazing.
Hey do you know how to run ipadapter in forge or you know any other image generator in automatic 1111 image quality but run faster also gives a lot of controls like comfyui like ipqadapter faceswap consiatency and others
@@11_amankumarmall14 Try Fooocus so handy find this channel on youtube there are so many tutorials "Kleebz Tech AI" I can not give you link if you use link your comments automaticly deleted by youtube
Whilst ComfyUI is definitely harder to grasp initially as a beginner, I've found it a lot better with regards to actually teaching you what stuff does since everything is exposed and editable under the hood, and thus examination of and modifications to the workflows of others that you download demonstrate more tangibly how the individual settings work off another to produce the final image
I think the biggest setback of ComfyUI for those just picking it up is the concept of Custom-Nodes. Trying to learn from the workflow of others can be extremely frustrating, because 9/10 you will be missing a node, and not even have any idea "Find missing Custom Nodes" in Node Manager (or even node manager: since it is pretty much a essential part of ComfyUI and does not come with ComfyUI by default) is a thing, AND even if you do know, chances are you will run into deprecated and even niche hard to find nodes not in the Node Manager repo. It's all a bit much to learn and keep track of. Going forward, I think making the workflows more streamlined and a better repo for nodes would make a big difference towards its adoption and retention rate.
Yea it can be a hard to deal with at times, think it would be nice if comfyui came with prebuilt workflows for popular workflows like controlnet and img2img which you could access from tabs, like in automatic1111.
This is what got me, and I'm a diehard Blender Geometry / Shader Node guy. It's messy and I already hate conda/pip work with Windows package management. So this takes that concept and makes it more modular so the custom nodes bash in the creative flow - that said i came here to get a nduget to jump back in. crazy that the vanilla download with the 'basic's is 50g. I I'm gradio'd out anyways
As a user of both, I'd say pick what you want, you still going to have to put your brain in gear when either of them break. That's when you really learn ! But auto then comfyui I'd say was a good way for me. At moment I'm going back to Auto to see what I missed while running comfyui for so long.
I think a useful workaround for some of the issues you have found in ComfyUI - which I've never actually used before, but am interested in learning, hence the reason I'm watching your video - is to create custom templates based on whatever workflow you need for a specific project, similar to how art programs have custom workspaces. Is this something that can be done in ComfyUI? If so, I would think it would make it more powerful than A1111, which doesn't allow those presets (to my knowledge, at least).
You can download extension from manager which allows you to store any workflow in folder like structure. You can also open one workflow on one tab and another one is second tab. Then you can start both of them and they both add to the queue. Browse pictures in output folder to see differences. Realistically though. I think you try adjusting your workflow like first 5 images and then you just fill the queue with the one you like the most.
To me it seems like one of those things that if you need it you need it. Otherwise just stick to ComfyUI. Most people only scratch the surface of A11111 as it is
I would say it is easier because you don't need to touch any settings files. It was so much hassle trying various arguments in A1111 for low vram having to restart the program every time. Not mentioning when A1111 crushes generation, you also need to restart the whole program.
Yeah Forge is a lot faster than 1111. And with Comfyui u will vaste hours and hours with errors from missing notes that it cant find automaticlay. i liked the idea of comfy, but have given up.
ComfyUI I only use if it is really necessary, If you use Forge WebUI over Automatic1111 that is huge performance boost especially if you have Low VRAM. Personally I use Fooocus WebUI it is so practical image quality is better with foocus V2 expansion and styles, in painting very good and handy face swap image to image more than enough. If you have low VRAM ist is so fast and esay to use SDXL lightning models. Performance presets amazing.
Will have to check both Forge and Fooocus out when I can
Hey do you know how to run ipadapter in forge or you know any other image generator in automatic 1111 image quality but run faster also gives a lot of controls like comfyui like ipqadapter faceswap consiatency and others
@@11_amankumarmall14 Try Fooocus so handy find this channel on youtube there are so many tutorials "Kleebz Tech AI" I can not give you link if you use link your comments automaticly deleted by youtube
how much vram is low, i have 4070 super 12gb vram, what ui can i use ?
Thank you for this video.
I just deployed Automatic 1111 last night, so I'm just getting into it and there is a LOT more to learn.
Whilst ComfyUI is definitely harder to grasp initially as a beginner, I've found it a lot better with regards to actually teaching you what stuff does since everything is exposed and editable under the hood, and thus examination of and modifications to the workflows of others that you download demonstrate more tangibly how the individual settings work off another to produce the final image
Excellent breakdown, thank you
I think the biggest setback of ComfyUI for those just picking it up is the concept of Custom-Nodes. Trying to learn from the workflow of others can be extremely frustrating, because 9/10 you will be missing a node, and not even have any idea "Find missing Custom Nodes" in Node Manager (or even node manager: since it is pretty much a essential part of ComfyUI and does not come with ComfyUI by default) is a thing, AND even if you do know, chances are you will run into deprecated and even niche hard to find nodes not in the Node Manager repo. It's all a bit much to learn and keep track of. Going forward, I think making the workflows more streamlined and a better repo for nodes would make a big difference towards its adoption and retention rate.
Yea it can be a hard to deal with at times, think it would be nice if comfyui came with prebuilt workflows for popular workflows like controlnet and img2img which you could access from tabs, like in automatic1111.
This is what got me, and I'm a diehard Blender Geometry / Shader Node guy. It's messy and I already hate conda/pip work with Windows package management. So this takes that concept and makes it more modular so the custom nodes bash in the creative flow - that said i came here to get a nduget to jump back in. crazy that the vanilla download with the 'basic's is 50g. I I'm gradio'd out anyways
great video man, like the plus minus point
Thanks so much!
As a user of both, I'd say pick what you want, you still going to have to put your brain in gear when either of them break. That's when you really learn !
But auto then comfyui I'd say was a good way for me. At moment I'm going back to Auto to see what I missed while running comfyui for so long.
So Automatic1111. Got it.
thank you very much for this video
Very helpful!
Very good!
I think a useful workaround for some of the issues you have found in ComfyUI - which I've never actually used before, but am interested in learning, hence the reason I'm watching your video - is to create custom templates based on whatever workflow you need for a specific project, similar to how art programs have custom workspaces. Is this something that can be done in ComfyUI? If so, I would think it would make it more powerful than A1111, which doesn't allow those presets (to my knowledge, at least).
you seem very confused. ComfyUI is the one where you create your own workflows and by your metric more powerful than A1111
You can download extension from manager which allows you to store any workflow in folder like structure. You can also open one workflow on one tab and another one is second tab. Then you can start both of them and they both add to the queue. Browse pictures in output folder to see differences.
Realistically though. I think you try adjusting your workflow like first 5 images and then you just fill the queue with the one you like the most.
To me it seems like one of those things that if you need it you need it. Otherwise just stick to ComfyUI. Most people only scratch the surface of A11111 as it is
7:38 - not really. You could save and load different presets ;-)
Why my comfyui generates images in seconds but my automatic 1111 takes minutes, even hours.
Real time generation
But what I dont understand most video tutorial said comfy UI is easier... what the hell
I would say it is easier because you don't need to touch any settings files. It was so much hassle trying various arguments in A1111 for low vram having to restart the program every time. Not mentioning when A1111 crushes generation, you also need to restart the whole program.
Neither, just use Forge. It's A1111 that runs on 4gb of graphics memory easily. It's better and faster and wont freeze up your pc.
Out of all three, Comfyui reign's supreme. Not only for the speed of generation but also for the mere ability to be more in control. :)
Yeah Forge is a lot faster than 1111. And with Comfyui u will vaste hours and hours with errors from missing notes that it cant find automaticlay.
i liked the idea of comfy, but have given up.
@renlow Seems like you newer actually used ComfyUI.
Neo Professor, You're fantastic! Let's be friends and have fun!