Stable Diffusion - Photo to Anime or Anime to Photo - Fooocus
ฝัง
- เผยแพร่เมื่อ 30 มิ.ย. 2024
- Master Fooocus and Stable Diffusion for Creative Image Generation! 🎨 In this Stable Diffusion video at the request of some subscribers I show how to change a photo to anime or anime back to a photo with Fooocus. This also will work for other styles as well. #Fooocus #StableDiffusion #DigitalArt #ImageManipulation #CreativeTools
This is part of my ongoing series of videos on installing and using Fooocus for Stable Diffusion. Fooocus is a great interface for using Stable Diffusion and is very easy to get started. It also will run on systems with only 4GB VRAM.
I am running on an i5 32GB RAM Nvidia 3070 8GB VRAM
If you find the video useful and would like to tip, TH-cam does have the Super Thanks option. Those are greatly appreciated so I can have my coffee!!
☕ BUY ME A COFFEE: ko-fi.com/kleebztech
Also I am a verified creator with Brave and do accept BAT for users of the Brave browser.
Download Fooocus: github.com/lllyasviel/Fooocus
How to install Fooocus video: • Stable Diffusion - Dow...
Fooocus Beginners Guide: • Super Easy Stable Diff...
Fooocus Upscales and Variations: • Stable Diffusion - Foo...
Checkpoints and LoRAs the Basics: • Stable Diffusion - Che...
Fooocus Poses and FaceSwap - Image Prompts: • Stable Diffusion - Pos...
Zoom with Outpainting: • Stable Diffusion - Zoo...
Inpainting with Fooocus - Don't Regenerate, Fix!: • Stable Diffusion - Inp...
Background Replacement with Fooocus: • Stable Diffusion - Bac...
Fooocus Tips and Tricks (and AI Hands) • Overlooked Fooocus Tip...
Stable Diffusion - Styles in Fooocus - How do they work?: • Stable Diffusion - Sty...
FaceSwap and Consistent Character TipsPart 1: • Stable Diffusion - Fac...
FaceSwap and Consistent Character Tips - Part 2: • Stable Diffusion - Fac...
00:00 Intro
01:05 Photo to Anime
10:30 Anime back to Photo
19:20 Anime back to Photo with Inpainting - วิทยาศาสตร์และเทคโนโลยี
If you need the anime checkpoint/model you can just run the anime.bat file instead of the run.bat file. It will download the checkpoint automatically when you first run it. Otherwise you can check out this video on how to get and install them: th-cam.com/video/GgEEb2K0j7s/w-d-xo.html
Wow! It's always amazing what's possible with fooocus. Thank you for today's revelation. ;-)
Thanks, yet again!
many videos are there about how to convert anime to real but none of them clearly covered real to anime, thank you for this!
Glad it was helpful!
12:53 I really really like that you left your trial and error in the video. I'll remember this better
Thanks. I find doing my videos this way gives people better idea of how things work.
This Ai Is Awesome In A creepy Way
Love U tuto keep Up ❤
best explanation ever!Thanks
You are welcome!
Very informative. Thank you
Thanks for watching!
Hi! thanks for the video, i was looking for how to convert anime into real, and this give me a lot of information about how to do it, and how to improve it!
Long story short, i was in a doze, when I miss click the performance button on fooocus... I used the "Extreme Speed" option, and the results are AMAZING!, then you can use one of them that you liked and make the same process again but in "Quality" perfomance, :D hope this help to make another video so someone can make it better and better!
Thank You!
You're welcome!
Thanks! Very useful information! Focus is an amazing tool, you just need to know how to use it)
Very true!
@@KLEEBZTECH my dream is to use Fooocus via API, I'm using Fooocus from the RunDiffusion service now, but plan to install locally (8GB, Mac...) - to experiment with the API
Thank you for the video! I hope the new SD 3.0 fixes this issue with hands when generating realistic images. I spend a lot of time fixing hands all the time.
I am not expecting it to be drastically better but hopefully some improvements.
Can we use sd3 in fooous?
Don't know if we will be able to. I would not expect it very soon though.
Not into anime but I like your presentation. Subscribed for more videos on the software thanks
Nor am I. lol. But I could not pass up the challenge of trying going back to realistic. It worked much better than I expected and also it can be used for other styles as well. Although some are more difficult than others. And thanks for the sub!
👍👍👍👍
we posted our video on this, it part of SD 1.5 transition between any checkpoints. Its best to use SDXL 1.0 with SD 1.5
Try this totally different method that is usually used to upscale but I use it with more realistic checkpoints to convert anime/painting into photos.
Automatic1111 --> Img2img and insert the image --> Control Net enable Tile/Blur and in another Control Net tab enable SoftEdge.
Play with the resolution to increase it but keeping the propotions an dalso play with the Denoising Strenght
I use Rev Animated as checkpoint
I will have to check it out next time I launch A1111. 👍Will admit I use it less and less these days.
Sorry for the question but Is there any way to set the exact number of Steps of Sampling? Thank you in advance. Great video!
In the Advanced tab, Developer Debug Mode, after the sampler and scheduler settings, there is a Forced Overwrite of Sampling Step setting
@@itsaboy213 Thank you!
Hey! When convert from anime to photo u didnt uncheck LORA, its intended or an error? Thx!
Very nice vid
sd_xl_offset is usually used with models like juggernaut so it was intentional. It is not necessary though.
I didn't know they started out with real images. So that was nice to know. I thought it was all done with a description of the scene. Some technical questions. What are system requirements, can you run this on almost any pc? Is this done locally or on the Stable Diffusion website? I love the results.
You can run locally but it is suggested that you have a decent video card. If you try running on a PC without a dedicated GPU then you need tons of RAM (32GB I think) and it will be very slow. There is a recommended specs and an idea of how it will perform on the Github page. There is also the option to run online with services like Google Colab which I do have video on but the free tier does limit how much you can do with it each day. Just avoid websites that claim to be Fooocus and are really not. github.com/lllyasviel/Fooocus?tab=readme-ov-file#minimal-requirement
Also my video on using with Colab. Do note that there are currently issues with it sometimes not giving a public link but that seems to be getting better. th-cam.com/video/07elsLQU6ho/w-d-xo.html
@@KLEEBZTECH Thank you for taking the time to respond with all that detail.
Hello, thank you so much for your video!
says i have more than 100 anime style images would like to turn into realistic style,
if there have any method to do batch generate in fooocus?
or i can only do it 1 by 1??
No batch options for that in Fooocus.
Hello, I'm looking for an out painting that is similar to in Paint anything, meaning I want to create a mask within the drawing and then do the out painting. Can you provide an example using masks?
I've tried doing this with in Paint anything, creating a mask over a person, and then modifying the background. However, it does it horribly, as it blends the original image as if it were part of the newly created image.
I want to add a background with a robot behind a person, and when I input that description, what the AI does is only create a robot using the person as if it were part of a leg or a part of the robot.
hey can we use this in multiple photos at once ?
If you mean using different images as image prompts, you can but you will get a mixture of the images. You can get some interesting results.
can you please make a vidoe on how to increase fooocus generation speed, i have rtx4050 140watt 6gb vram and it still takes 30sec to generate
It's loading in low vram mode altho I have 6gb vram
Definitely! I'm new to SD, but I might be able to help with increasing the cooling of your processor and video card, even doing a gentle overclock.
6:00 You have also a speed- button on the top right courner
and how to use this on A1111?
I am not familiar enough with A1111 to explain exactly how but A1111 should be able to with the img2img section. Some things I just prefer to use Fooocus for since it is easy to have them both.
Please can do how to turn anime to drawing? Or how can i create drawing book using foocuse please 😢😢
You can do something similar and use the styles in Fooocus to try and get it to change to the style you like. I am not sure I fully understand what you mean by drawing book exactly.
@@KLEEBZTECH I mean like foocuse give you drawing of eyes for exemple and give you shadow to draw the same thing
Maybe if you have some sort of example of a book that would help me understand fully. I think I have an idea what you mean but not 100% sure. @@musicalstation101
@@KLEEBZTECH like drawing books for kids that sold online for exemple
@@KLEEBZTECH and can you do how to turn like the pic u generated to hand drawing pic with fooocuse
@Kleebz Tech AI , many thanks , but how to install more Base Model , since i only have juggernautXL_v8Rundiffusion.safetensors
And here is the answer 👍: th-cam.com/video/GgEEb2K0j7s/w-d-xo.html Will note that if you want to grab the anime checkpoint then you just need to run the anime.bat file and it will download it. Otherwise this video will explain how to get more.