<h1 id="@alphonse-mucha">@alphonse mucha</h1>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.There are 171 Alphonse Mucha artworks registered on <a target="_blank" rel="ugc" href="https://www.wikiart.org/en/alphonse-mucha/all-works/text-list">WikiArt</a>, and this LoRA was trained on all of them randomly. The dataset includes not only Mucha's famous Art Nouveau decorative style, but also other types of works such as self-portraits, sculptures, and oil paintings. Therefore, this LoRA is also intended to generate those less commonly associated aspects of Mucha's work.For tagging, I used "<a target="_blank" rel="ugc" href="https://huggingface.co/SmilingWolf/wd-eva02-large-tagger-v3">SmilingWolf/wd-eva02-large-tagger-v3</a>", and for natural language captioning, I used "<a target="_blank" rel="ugc" href="https://huggingface.co/mradermacher/Qwen2.5-VL-7B-Instruct-heretic-i1-GGUF/tree/main">qwen2.5-vl-7b-instruct-heretic-i1</a>". I combined the outputs of both systems into a single TXT caption file. However, I am not fully satisfied with the accuracy of either method.The former, in particular, frequently produces incorrect tags, such as miscounting the number of people or hallucinating objects that do not exist in the artwork (for example, tagging "mask" when there is no mask, "weapon" when there is no weapon, "deer" when there is no deer, etc.).Despite these imperfect captions and inaccurate tags, Krea 2 is still able to generate reasonably good results. Even with such a rough captioning process, the model performs surprisingly well.However, the recognizable "Art Nouveau decorative elements" tend to appear quite strongly, and those decorations are often generated in circular or ring-like patterns.

@alphonse mucha

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

Files with SHA256: 83e0f9b5b9fce53b0c2dd8891ba92fe636526b4f6f0ccefe71ec79fd117d9ded