Magic prompt completion model trained on a dataset of 80k Stable Diffusion prompts. Base model: TinyStories-33M. Inspired by MagicPrompt-Stable-Diffusion. Model seems to be pretty decent for 33M params due to the TinyStories base, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it’s decent. Whether you would use this over a small GPT-2 based model is up to you. Best generation settings I found: maxnewtokens=40, dosample=True, temperature=1.2, numbeams=10, norepeatngramsize=2, earlystopping=True, repetitionpenalty=1.35, topk=50, topp=0.55, eostokenid=tokenizer.eostokenid, padtokenid=0 (there may be better settings). norepeatngramsize is important for making sure the model doesn’t repeat phrases (as it is quite small). «found footage of a ufo in the forest, by lusax, wlop, greg rutkowski, stanley artgerm, highly detailed, intricate, digital painting, artstation, concept art, smooth» «A close shot of a bird in a jungle, with two legs, with long hair on a tall, long brown body, long white skin, sharp teeth, high bones, digital painting, artstation, concept art, illustration by wlop,» «Camera shot of a strange young girl…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Technotech
Теги: gpt_neo, completion, en, endpoints_compatible
Лайков: 2 | Загрузок: 269
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
