razster
Joined 12 years ago
Joined 12 years ago
Anyway, if you know of VAV VGX then welcome thus the three hands remark.
I use the Portable version of ComfyUI, most are done with Qwen Image 2.1 and some hard restores using FIBO2. You can find a bunch of video tutorials on YT for both models.
These 2 diffusion models are amazing.
I've also started using Flux.3 Klein for extra added details. Local diffusion models are so great.
Going forward, I’ll be using local diffusion models exclusively, and I couldn’t care less what others think. This workflow suits me perfectly, and I genuinely enjoy the process. I have over 100,000 digital and film photos I've slowly been processing using this method - I have restored photos I tried to restore the older ways without success. I'm so grateful for these local models.
https://pastebin.com/FAdBbGUd Qwen3.8-27B on an RTX 3090: Inference Options and Benchmark Results
No need to pay for a thing, except electricity, which that is the next step, solar powered LLM server.