ModelListedExternal

@Alphonse Mucha

First of all, I want to clarify that one of the main purposes of training this LoRA was to automate the captioning process through vibe coding.

KindLORABase modelKrea 2Version

Model source

Source description

Initial.

dim16/alpha16, unet 1e-04 (adamw8bit / cosine), 1024res, 171 images / 2000 steps

Sources

1 source

CivitaiPrimaryVersion 3176581

Verified Aug 24

Model artifacts

1 artifact

@alphonse_mucha_krea2_v0_0_0_epoch_10.safetensors

safetensors · BF16 · 109 MB · SHA-256 83e0f9b5b9fc…9ded · Civitai

Source excerpts

1 excerpt

Source context: 573 downloads · Type LORA · Base model Krea 2