Initial (experimental). You can access the prompts for the showcase images by opening them in ComfyUI, or by viewing them at https://civitai.com/models/2689816 A LoRA weight of 1.5 or higher is recommended. Pixel-perfect results are not guaranteed. The LoRA often produces ambiguous or poorly defined pixels, so artifacts may need to be removed using tools such as the PixelOE node. Captioning was performed almost entirely using Danbooru tags, with the same captions as the Krea 2 and Anima versions. The captioning method recommended in MOSS's USERGUIDE.md was not used. LORA, MOSS Image Base, dim32/alpha32, AdamW8bit, LR 1e-4, constant 1700steps, 100images(x8 scaled), 1024² res.