Видео

@@WanderlustWithT no problem :)

Welcome :)

Of course this tutorial is not for everyone. Yes using proper techniques you can do a lot with photoshop and photography tools. I use to be a commercial photographer and some of my images out of camera and on film were scanned in at 100mp or higher then upscaled for specific jobs. For the average person though, that is unnecessary. The point of the stack was to show that upscales can be stacked. So if you are just looking for an all in one solution this was one of the best methods at the time of recording. That said there are new upscaling techniques that have since provided better results and less compute intensive. But also trying to compare this to large format photographs is not the point of this video or in the scope I was going for in this video. I appreciate your input tough.

So the way I do this is by setting the latent image width in the range of the trained image in the same aspect ratio. So I use a ratio plugin. Then from there I will upscale to the native resolution of the monitor or what ever use I may need. Now for ultra wide what I would do is go slightly above the ratio and crop down or smaller and crop in. Because the trained image is 1024x1024 you need be be careful going outside of that as it can cause tiling and rendering issues. Using known good ratios will solve this.

Thank you so much, I got more videos coming I have just been away from home so haven't fully got a chance to do anything with channel for a bit.

Yes absolutely I have done a bit of video in comfy and swarm. I fact in the new swam ui there is a video tab that said I’ll create a work flow that makes it a little better

i have not tried swarm yet so please if you could let me know if that feature is pending or live ? thanks@@AIMadeEasier

That's awesome thank you so much for the comment!

He has moved it to here tensor.art/models/642019060365894429

In programming when you write and compile for a certain version number sometimes the things in updates to later versions would need to be programmed differently and my unstable for certain tasks. Hence why Python is version specific. It could likely be reprogrammed for a new version of python but why change what works. Git is always installed on my computer just because I work a lot with GitHub and my own git repositories. It’s not always needed for the install but is used more for adding plugins. Some installers I believe now include git as well. Dreamshaper vs Dreamshaper XL Dreamshaper is based on stable diffusion 1.5 (faster but not always the best results, Dreamshaper XL is based on SDXL which was the major upgrade last year that improved results hugely. It does also require a higher starting image size so a little slower but the results are way better.

Thank you so much

No not really you would need to export all the frames of the video back to image then upscale each image and then recompile back into a video file. There are tools out there for video upscaling though that would be much easier.

Doubt it but what error are you getting?

That’s odd have you updated the comfy ui manager. Also if you installed a while ago there is a new version could be causing the problem.

Checkpoint models are the files that give the weights to generate the image your request. So it’s looking through the trained model and choosing the weighting based on your prompt. As for the setting in a png it comes down to meta data. Meta data is able to hold a bunch of text or code that can be decoded by the comfy ui interface and others. In this case it’s mostly plain text. I can show an example some time. I’m thinking of doing a questions and answers video coming up. Just finished off my new setup for recording, new microphone and all looking forward to it.

@@AIMadeEasier Wow! Thank you for your quick response! Much appreciated!! 🙂

commas are ignored its just for our own visual pleasing

Thank you so much!

Yep I almost have my new setup completed

Love that you got it working! It’s so much fun.

I would try both but likely after the upscale will yield better results. As for which are more friendly towards photos and illustration so far I find the 4x Ultra Sharp is great for illustrations. It can do well with images that are already a decent size but we are starting to see more and more AI based upscaling which uses more of an image generation mind set which can reduce the amount of noise. That said any fine details like text, or objects the AI can not detect turn out to look a little weird. Text is a great example, it turns our looking like an alien language if it's to small. This is because AI Upscalers just like image generation has not been trained on text and has no clue what it is, so in some cases traditional upscaling methods will still be required in photographic upscaling. I was a professional photographer for years and I remember always trying to push my raw images out as large as I could to see what would happen, trying to find new techniques to get the scale I wanted. In most cases for printing it was unnecessary as if your printing off a really large poster or doing a billboard for example. The viewing distance is further than say something like a 4x6 printed image in your hands. Now that said if you need a larger upscale than something like 4X it may be worth the time to generate in a larger size first and then up scale only that 4x. Another amazing trick is if it's an illustration like a vector image, once created bring it into Adobe Illustrator and use the Trace Function. Work with it to get the vector to what you want then you have a vector image you can scale to any size with out worry.

Thanks for your feedback glad it helped :)

No Problem! Hope it helped

It depends what your end goal is. If you need a really large image; you may need to use something a little more powerful or in the cloud. So it really depends on your end goal. I am working on a video about running stable diffusion in the cloud and how to do it on a budget.

@@AIMadeEasier Not really large. Just doubling a 512 x 768 image. It takes me around 10 minutes per upscale, which is a bit longer than what I'd like. I don't know if there's a faster option.

Yeah sorry my recording space is not quiet always so I use the music to cover up the tv on in the background and the kids playing lol

That's an awesome tip thank you! I love using drag and drop and clipboards for being more efficient

you're a fkn legend sir

Thank you

Can you please point me to a video for upscaling with adding details in comfy? THX!

If you only want to do straight upscaling, then ComfyUI is a slow and "expensive" i.e. GPU power and time... way to do it. Use an online or dedicated upscaler like Topaz or Upscayl and get faster and better results. The proper way to use upscale in Comfy or A1111 is to do Latent Upscaling, thereby adding more detail by utilizing latent space. Similar to HiRes Fix.

@@TheDocPixel Intresting you say that. I found and adapted a workflow that iterates adding detail as it scales, yes quite slow but what a great job it does. The larger I go the more detail it adds. Straight upscalers just don't work for me. They get bigger sure but something is always sacrafised.

@@uk3dcom - I agree... and also have adapted Detweiler's workflow. The results are stunning when also adding an upscale model.

​@@uk3dcomI am looking for a workflow that adds detail and not just upscale. What would you recommend?

This is extremely likely. Upscaling requires a bit of horse power. You could try a lighter upscale model from that list and try and run it multiple times. Although not ideal. There is two reasons for a box to go red. #1 the node is not installed (up scaler is pre-installed) so we know it's not that. #2 the node had an error running (lack of v-ram, incorrectly configured ect...) Most stuff these days for Stable Diffusion they recommend 6gb vram or higher, I would not go below 8 personally. Depending if you have the budget or what not, it might be worth looking at a new card. A great example of a budget card is a 3070 used or even a 4060 as these cards are fairly inexpensive and work well with stable diffusion. If your on a laptop then once again depending on your budget might want to run in Google Collab or even using a cloud based solution. How ever with cloud based solutions, if you forget to shut it down can cost you the price of a 3070 used in a single months time. So just be aware that cloud based solutions can be extremely expensive. Example: Paperspace on their basic tier. The basic tier is $0.46 per hour so if you forget to shut down the server when not in use your monthly cost could be as high as $355. That said if you are using it lightly and you are diligent about shutting down the server than it may be more affordable. Just with the risk price of $355 and a used 3070 going for around $300 these days... You get where I am going.

thank you so much, I tried other Upscaler and it worked @@AIMadeEasier

@@sc0peAI yeah depending on the upscale will use more or less ram. If you can find a low vram upscaler that is almost lossless you can stack them. So 2x-2x until you hit your vram limit.

You know I love that model also just got the other model downloaded a testing. In initial tests I love it too

​@@AIMadeEasierI know thanks for that 😉👍

I agree, and I think it will open up more ideas for traditional artists who embrace the technology

@@AIMadeEasier Yes. Considering the AI's has been trained on billions of pictures, we can merge arts like never before, which in turn creates new artform. This has never been possible before. I have created some real spectacular art that I never seen before. I am being really protective of my art until the day we can copyright it. And be sure that day will come. Thing is that the filters, seeds etc are always changing, sp the art I am able to create today, might not be possible in the future, which makes it real sensible to protect my art. The art I for example post on Facebook, is like 10% of what I have really created as my "best" pictures. But I am not doing it for the money, that is not the reason I do this, I do it because I love creating art with AI. Hopefully peopole will one day appreciate what I have created after we can copyright it.

@@nn-db4fw Thank you so much for your input. I love to hear it from both perspectives. For me the copyright case that happened the ruling really bothered me. Not in the ruling it's self because it's a complex question, but in the statement made by the judge that AI can't create emotionally impactful images. We good prompting you certainly can get extremely impactful images, and something I have been playing with for a bit. I studied the history of photography for about 20 years and the thing I loved was how when the camera was accepted by artists, framing in traditional changed to match the new medium. I am excited to see where this takes us in the future as the tools in this early stage are really incredible.

@@AIMadeEasier Yes, we are only on "generation 1 AI art" as for now, and we all are amazed by what it can do. In a few years we are on "gen 2" or maybe even "gen 3" AI art and we can only imagine what AI art can produce when it is able to be creative on it's own, which will happen. There was a huge debate when the cameras came out and if that was really a new form of art as it was "only to click one button". before that, people had to stand beside say a river and paint the scenery maybe for days, weeks or even months. Then the cameras came and with one click the scenery was captured. I fully understand the cameras was controversial back then, but today the cameras are fully accepted. AI art is pretty new and soon that will be accepted as artform as well. It takes a LOT more work to be able to create say a good portrait with AI art than with a camera. All the things one needs to know all from angles, mood, lighting, distance and whatnot. Then we have all the things we can add into the portrait that most who takes pictures won't ever be able to do; like taking a portrait of someone on the moon, or on the bottom of the sea, inside a volcano, balancing on top of a flagpole etc etc. The AI understands these things, and that is fantastic if you ask me. As I see it, the AI art blows photographies out of the water in most areas. Hopefully we will have a new debate and new revised laws regarding AI art no later than Gen 2 or Gen 3 AI art.

I can start saving them for you guys and I’ll upload them to a git hub account I’ll set it up in the morning with my workflows :)

@@AIMadeEasier that's great looking forward to it

You can technically do either but I prefer to do it as a new install. Just so there is no chance of messing up the full integration of using the new interface. Now you could reroute your models folder using the extra_model_paths.yaml how ever one install all integrated is all I needed. So I just moved everything over to this and don't use my original install anymore.

Hope it helped! I really love this UI and can't wait to see as it matures. It does not feel like an alpha level of production to be honest, it feels like a finished V1. So it will be insane to see where they take it from here.

That’s what I love to hear!

In the Ksampler control_after_generate set that to randomize

Thank you, hope it helped.