วีดีโอ

Doesn't look natural

Thanks, I've been looking for how to upload a model for a long time.

Not working no such file or directory showing

can we use this in comfy ui with rtx 4060 with 8gb vram?

I couldn't manage to install flux dev, I select the model, it gets stuck in the processing stage, probably I couldn't manage the settings.json, can you help me how should it be done?

Thanks a lot. My graphics card has 8GB of RAM, can I Upscale in this way?

can i do it with gtx 1660 ti?

For some reason, when I upscale the image turns out quite grainy...also I don't understand what difference the "refine" checkbox does when upscaling, as you can also not select it, and how to tweak it. Must it be set to the same model you used to generate the image? what happens if you leave it blank? - Suggestion for next: Character consistency for a graphic novel! Thank you for all your hard work.

May I ask something? My GPU isn't good enough for Krita AI so I'm using the "Online Service" (GPU cloud). Can i still use the models I find in this video? I downloaded them and put them in the folder but krita doesn't see them in the list unless I switch to "local managed server". For example, how would I generate a pixar style image with the online service without the model?

i got this error : import error: No module named 'triton' pls help me

Is this website still working? i’m getting the error ERR_NGROK_3200.

Thanks for the tutorial, finally a good tutorial

Ty ❤

hello,I couldn't see how to install Krita :/

why don't you use flux+krita?

Thx. Could you please make a walkthrough of the different extensions that comes with forge?

does it work on a 4060 8gb?

hey, can you please give me any link from where I can download Build Tools for Visual Studio 2019. I have tried many sources, but couldn't find it on internet. The paramidflow is also not installing it.

Greetings. Does it work with Flux?

No it's not good. Not photorealistic. I think you used a bad model checkpoint. I got better results with Krita.

Most things learned on 12 minutes on my life:

Krita is really a game changer, the best of both worlds. It makes controlnet pratically useless if you know what you're doing.

Great job, well explained!

Thank you friend, I'm saving all your videos and hope I get some more time to practice with krita soon, you're a gamechanger!

in 7:38 i couldnt install the server Win5 error access denied but i install to other location instead

yeah i like this

Очень хорошо!

I like your Krita series keep up with your good work Thank you.

hi, your website is down, how to download the missingfiles please

We have to install it before using ?

Does it have any collabs available

Exists perfect program LinkShellExtension Very easy for use ) Contains tons variations for making symlink/hardlink/junktion point

Thank you for the lessons! I hope in this program I will be able to combine two images into one (real image with generated one) with normal color correction! Thanks again for the information!

vert helpful bro. nicely explained

Usefull info buddy ❤

I got error message in generated Ouput window..what should I do?

I get this error WARNING:root:WARNING: No VAE weights detected, VAE not initalized. WARNING:root:no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded. Failed. Trying to load as unet.

can you make a GGUF for LMStudio? TIA

flux is more of a issue then others

ltx install google colab. Please creating video I am waiting 😢

Wow, bro!! This worked really well. I also tested dev models, and they worked pretty well. I also added a Lora, and it also worked. Thank you so much, bro!!

This is great but I have some questions: 1) when we browse civitai should we stick to models that work for 1.5 or is Krita adaptable to new versions? 2) are we required to add the lora prompt Keywords all the time in our prompts? What's then the purpose of downloading a lora that makes, I don't know, bearded vikings, if we must add "bearded viking" as a keyword all the time? And negative prompts too? 3) I sadly got a little lost with the VAE, I understood the checkpoint you downloaded was missing something important but that s as far as I got. I'm still very grateful for your videos and will keep following you, if possible I'd love the next to be on keeping character consistency in subsequent generations, this is what got me into checkpoints and Loras to start with. Thanks again for the great content.

I have an issue TypeError: empty() received an invalid combination of arguments - got (int, int, dtype=str, device=torch.device), but expected one of: * (tuple of ints size, *, tuple of names names, torch.memory_format memory_format = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False) * (tuple of ints size, *, torch.memory_format memory_format = None, Tensor out = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False) Failed to load flux1-schnell-Q3_K_S.gguf LoRAs loaded: [] ERROR: Can only use SDXL, SD3 or Flux models

openposeai down?

i dont have the guuf_clip1: "flux_clip_1.safetensors" in the github wiki. Only "clip_g": "clip_g.safetensors", "clip_l": "clip_l.safetensors", "clip_t5": "t5-v1_1-xxl-encoder-Q6_K.gguf", "gguf_vae": "ae.safetensors"

Thank you!, I appreciate the help you give us

Installed yesterday (6-7 hours😒) but "error" occurs in preview window when it start to generate 😒😒

hmmmmm

Is it possible to create banners?

tysm