Software Engineering Courses (SECourses)•16mo ago

tried settings for upscaling from this video https://www.youtube.com/watch?v=HKX8_F1Er_w&t=746s but

tried settings for upscaling from this video https://www.youtube.com/watch?v=HKX8_F1Er_w&t=746s but the generations arent looking to good

YouTubeSECourses

Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD We...

Do not skip any part of this tutorial to master how to use Stable Diffusion 3 (SD3) with the most advanced generative AI open source APP SwarmUI. Automatic1111 SD Web UI or Fooocus are not supporting the #SD3 yet. Therefore, I am starting to make tutorials for SwarmUI as well. #StableSwarmUI is officially developed by the StabilityAI and your m...

Xxlads tried settings for upscaling from this video https://www.youtube.com/watch?v=HKX...

Furkan Gözükara SECourses•9/9/24, 1:35 AM

best is supir

Furkan Gözükara SECourses•9/9/24, 1:36 AM

https://youtu.be/OYxVEvDf284

YouTubeSECourses

Complete Guide to SUPIR Enhancing and Upscaling Images Like in Sci-...

In this video, I explain how to 1 click install and use the most advanced image upscaler / enhancer in the world that is both commercially and open source available. The upscaler that I am going to introduce you is open source #SUPIR and the model is free to use. SUPIR upscaler is many times better than both paid Topaz AI and Magnific AI and you...

Furkan Gözükara SECourses•9/9/24, 3:13 AM

starting testing T5 training

Furkan Gözükara SECourses•9/9/24, 3:18 AM

wow it added some quite VRAM

FFurkan Gözükara SECourses wow it added some quite VRAM

dsienra•9/9/24, 3:20 AM

how much? fits on 24gb cards?

Ddsienra how much? fits on 24gb cards?

Furkan Gözükara SECourses•9/9/24, 3:22 AM

i didnt test 24 gb yet

Furkan Gözükara SECourses•9/9/24, 3:22 AM

but in 16 bit added like 8 gb more

Furkan Gözükara SECourses•9/9/24, 3:22 AM

may barely fit to 24 gb

dsienra•9/9/24, 3:24 AM

tahnks, I'll be waiting your results

Furkan Gözükara SECourses•9/9/24, 3:36 AM

7 different T5 trainings started lets see tomorrow hopefully the results

dsienra•9/9/24, 4:14 AM

I heard that onetrainer is 2x faster on flux training

dsienra•9/9/24, 4:15 AM

but there is some incompatibility with forge, is diferent lora format, and to train you need flux models on diffusion format

dsienra•9/9/24, 4:16 AM

the forge incompatibility will be fixed sood, by onetrainer or by forge idk really

Ddsienra but there is some incompatibility with forge, is diferent lora format, and to t...

JohnDopamine•9/9/24, 4:51 AM

Fixed this morning: https://github.com/lllyasviel/stable-diffusion-webui-forge/commit/44eb4ea83797b2abcc2dcc3e0bfcbed77e5f7a6e

GitHub

Support T5&Clip Text Encoder LoRA from OneTrainer · lllyasviel/stab...

requested by #1727
and some cleanups/licenses
PS: LoRA request must give download URL to at least one LoRA

Buğra Alperen Uluırmak•9/9/24, 6:41 AM

Hello, I am working on fine tuning on stable diffusion xl and I am using my own interface. I have a couple of problems. I want to limit the number of colors the user wants. For example, if the user chooses 5 colors, the model should use only 5 colors can be less. The other problem is the tiling process. There are a few problems in this too. I would be happy if you help.

Ddsienra I heard that onetrainer is 2x faster on flux training

Furkan Gözükara SECourses•9/9/24, 9:33 AM

just impossible with same config

FFurkan Gözükara SECourses best is supir