Quantized (Q4_K_S) version of the amazing 🟡STOIQO Afrodite | FLUX model, all credits to the original author ALIENHAZE .
Why I made this quantized version? because my gpu is not powerful enough to run the full version and I thought it would be useful for everyone else who like me want to try a version of this wonderful model but for our humble gpus. 😅😁
If you want to know more details of the original model as version information or Recommended Settings, I invite you to go through the original model page and give a lot of love to its author😊.
Description
Quantized GGUF Q4_K_S
FAQ
Comments (5)
does it matter what clip is used here? fp8 vs 16 vs some of the new city96 ones?
🤔 I use t5-v1_1-xxl-encoder-Q3_K_L.gguf and
ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors
why not a Q8?? will be better than 4k_s and even closer to original...
Yes, you are right... but in my case the quantized version of Q4k_s is the one I can run in my setup.
No one wants to use GGUF files types due to their restrictive needs, unless of core you want to live with Migraines all the time. rebuild them to normal specs maybe I'll download them. My phone can not! run your giant files