Software Engineering Courses (SECourses)•12mo ago

Anyone that has trained loras locally with a 3060 using kohya?

TTimson try reducing Mask Blur

Flakdragoon•1/26/25, 7:24 PM

this is with mask blur 0. if I just gen it with the same prompt in flux dev, will it make the image more cohesive?

FFlakdragoon this is with mask blur 0. if I just gen it with the same prompt in flux dev, wi...

Timson•1/26/25, 7:27 PM

you can just gen over this specific area with no prompt and flux should fix inconsistencies

Timson•1/26/25, 7:27 PM

if you play around with creativity and normalization settings

TTimson if you play around with creativity and normalization settings

Flakdragoon•1/26/25, 7:27 PM

just to confirm, by normalization do you mean "init image reset to norm"?

AAiInfluence and let flux handle the inpainting?

Timson•1/26/25, 7:27 PM

pretty trivial impaint

mini-whiteboard-mock-up-for-copy-space-3d-rendering.png

1924-white20board20with20colorful20very20detailed-sasb-1-2400-517543648.png

TTimson pretty trivial impaint

AiInfluence•1/26/25, 7:29 PM

something like this but with an image of my own , how did d you do that

AAiInfluence something like this but with an image of my own , how did d you do that

Timson•1/26/25, 7:31 PM

just regular inpaint. This is generatied, it won't work with your own image

TTimson just regular inpaint. This is generatied, it won't work with your own image

AiInfluence•1/26/25, 7:32 PM

Ok so it's better to make a model of it got it

AiInfluence•1/26/25, 7:32 PM

Do you know where I can find a list of stable diffusion classes?

FFlakdragoon just to confirm, by normalization do you mean "init image reset to norm"?

Timson•1/26/25, 10:03 PM

yep, sometimes it helps

AAiInfluence Ok so it's better to make a model of it got it

druhl•1/27/25, 7:35 AM

Why not just do this with photoshop/ Canva?

druhl•1/27/25, 7:36 AM

You can also composite the image and do a very light Ksampler pass to blend it in, but if it still changes stuff for you, why not just use photoshop?

Ddruhl Why not just do this with photoshop/ Canva?

AiInfluence•1/27/25, 10:55 AM

blending issues

AiInfluence•1/27/25, 10:56 AM

Also I'm experimenting on fluxs capabilities

druhl•1/27/25, 10:59 AM

So there is a compositor V3 node. You need to feed it images, place 'em where you need and then do a very light refiner-like pass

AAiInfluence Also I'm experimenting on fluxs capabilities

druhl•1/27/25, 11:00 AM

Give that a try

AiInfluence•1/27/25, 11:00 AM

Is there any tutorial I can watch?

Ddruhl Give that a try

AiInfluence•1/27/25, 11:00 AM

Also in on SwarmUi

Timson•1/27/25, 11:23 AM

Has anyone tried installing swarmUI on ramdisk to speed up t5xxl/clip/vae switching for fp16 workflows on 24GB VRAM cards?
Current process seems grossly inefficient on machines with huge RAM - why this models can't be always loaded in RAM for near instant swapping to VRAM (6GB/s)?

Timson•1/27/25, 11:27 AM

I don't seem to understand what is the bottleneck for this operation. Suspect comfyUI always unload models from RAM cache after loading to VRAM that causes extreme slowdown of this process

druhl•1/27/25, 2:36 PM

You can install things on the RAM? Lol

AiInfluence•1/27/25, 3:09 PM

@Furkan Gözükara SECourses any comments on Deepseek R1?

42069•1/27/25, 4:53 PM

https://github.com/deepseek-ai/Janus

GitHub

GitHub - deepseek-ai/Janus: Janus-Series: Unified Multimodal Unders...

Janus-Series: Unified Multimodal Understanding and Generation Models - deepseek-ai/Janus

42069•1/27/25, 4:54 PM

DeepSeek Janus Pro just released

42069•1/27/25, 5:44 PM

Multimodal LLM capable of text to image

daroth•1/27/25, 9:58 PM

not impressed

daroth•1/27/25, 9:59 PM

daroth•1/27/25, 10:00 PM

Hunter•1/27/25, 10:05 PM

@Furkan Gözükara SECourses thank you for all your work. I have created a finetuning model of myself and the result so far have been quite awesome! I need to learn a lot more on prompting, but its very easy to get quite good results! If you have any tips to learn realism prompts that would be cool!

Timson•1/27/25, 11:18 PM

Flux's ability to establish coherency never ceases to amaze me. Here is an example how model both perfectly simulated art style of an old HoMM 2 game to create a new unit but also established battelscape rules of units hex and troop counter when asked to add new non existing "purple sorceress unit" with nothing but this single image

Timson•1/27/25, 11:19 PM

this one without troop counter but virtually indistinguishable art style from the original. Both examples just base flux dev no loras

watersocks•1/28/25, 12:36 AM

is face fusion still working on massed compute? can't seem to get it to install

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•1/28/25, 1:11 AM

Guys ,any advice on how to get Crystal clear face? Currently using my fluz fine char checkpoint, then some face detailing, but it always feels blurry or fake...

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭Guys ,any advice on how to get Crystal clear face? Currently using my fluz fine ...

Hunter•1/28/25, 1:17 AM

Have you tried upscaling with supir? Also how much % of the photo does your face take up?

Hunter•1/28/25, 1:17 AM

if its a small %, then you could try face inpainting, could be worth doing anyways. also have you tried adding words to your prompts that mean things like high-quality?

Aikage•1/28/25, 2:01 AM

<segment:face>

Aikage•1/28/25, 2:01 AM

Swarmui ftw

Aikage•1/28/25, 2:02 AM

Not sure how In comfy probably like 18 different mask nodes, a PhD, and three different rituals to elder gods

TTimson Flux's ability to establish coherency never ceases to amaze me. Here is an examp...

AiInfluence•1/28/25, 8:38 AM

is this possible with a Lora too?

Elli_Oaken•1/28/25, 1:26 PM

Hi! I have a question about this new Hunyuan Lora training method https://www.unite.ai/how-to-train-and-use-hunyuan-video-lora-models/
I was wondering if it willl interfere with the furkan-way comfyui installation as everything needs to be installed in a specific order? Or if it's advisable to train in any other way?
Like example https://github.com/tdrussell/diffusion-pipe
https://github.com/Nerogar/OneTrainer

Unite.AI

How to Train and Use Hunyuan Video LoRA Models

This article will show you how to install and use Windows-based software that can train Hunyuan video LoRA models, allowing the user to generate custom personalities in the Hunyuan Video foundation model: Click to play. Examples from the recent explosion of celebrity Hunyuan LoRAs from the civit.ai community. At the moment the two most popular ...