krea2turbo_Cyrano INT4

( Not my Model )


 <a href="https://civitai.com/models/2939391/krea2turbocyrano-int4?modelVersionId=3342130" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2939391/krea2turbocyrano-int4?modelVersionId=3342130
 </a>




 About this version


 INT8 models are compatible


 Preference parameters: SDE SIMPLE, 8 to 12 steps


 10 steps without LoRa and 8 steps with LoRa seems like a good compromise

Krea2_Cyrano2 int8

( Not my Model )


 <a href="https://civitai.com/models/2939391/krea2turbocyrano-int4?modelVersionId=3327693" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2939391/krea2turbocyrano-int4?modelVersionId=3327693
 </a>




 
 First test of the Krea2 Turbo INT4 model
 
 NEW 6.9 GB NVIDIA
 
 RTX 20 and later versions
 
 — small
 
 and
 
 fast on older graphics cards.


 Model merger using a short script created by ChatGPT


 model used for merge
 <a href="https://huggingface.co/Hippotes/Krea-2-Experiments/blob/main/krea2_turbo_int4-convrot-simple.safetensors" rel="noopener noreferrer nofollow" target="_blank">
 https://huggingface.co/Hippotes/Krea-2-Experiments/blob/main/krea2_turbo_int4-convrot-simple.safetensors
 </a>


 generation parameters


 euler simple 8 steps 1080*1440_1024*1536_972*1296