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 ChatGPTtemplate to use for the merge <a target="_blank" rel="ugc" href="https://huggingface.co/Hippotes/Krea-2-Experiments/blob/main/krea2_turbo_int4-convrot-simple.safetensors">https://huggingface.co/Hippotes/Krea-2-Experiments/blob/main/krea2_turbo_int4-convrot-simple.safetensors</a>parametres generationeuler simple er sde simple __8 steps 1080*1440_1024*1536_972*1296_ 896*1152Thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/PrincesOfDarkness">https://civarchive.com/user/PrincesOfDarkness</a> for the buzzINT8 models are compatible___ use forge neo classicPreference parameters: ER SDE SIMPLE and ER FlowMatchEulerDiscrete, 8 to 12 steps12 steps without LoRa and 8 steps with LoRa seems like a good compromise<h3 id="this-model-mainly-generates-paintings-or-images-not-ideal-for-realism-and-nfc-content">This model mainly generates paintings or images, not ideal for realism and NFC content</h3>

krea2turbo_Cyrano INT4

INT8 models are compatiblePreference parameters: SDE SIMPLE, 8 to 12 steps10 steps without LoRa and 8 steps with LoRa seems like a good compromise

Files with SHA256: 75f4dfa128cddd2012f0de92296f09bb4f89a9477d4d11311c5ffcd672275138