https://civitai.red/models/2385278/animayume?modelVersionId=3300637 Animayume_v15_base.safetensors SHA256: 16354589C360B1690842C4C4D04046C35AD4DE4516B15A06AC7AA350DC3265F2 For version 1.5: This version was fine-tuned on Anima Base v1.0 using a variety of datasets, including Danbooru, e621, Gelbooru, and Konachan. The dataset used to train this version contains 5 million images (all data collected up to August 6th, 2026), with nearly 25 million captions across different caption types (e.g., tags, natural language, chain-of-thought, etc.) corresponding to those 5 million images. This version was trained for 12 epochs and was just finished on September 5th, 2026, so I haven't had enough time to conduct extensive testing yet . This is currently a base version without any aesthetic tuning. This version can easily understand many concepts from e621, Gelbooru, and Konachan. Moreover, a large number of characters have been added to this version, including characters from almost all anime released during Summer 2026. It can generate their general appearance, but the results may not be very accurate because there is not enough training data for these characters. For a more comprehensive comparison, I have included comparisons between this version and Anima v1.0, Anima 2.9B, and Anima Aesthetic 1.1 in the gallery. In this version, i recommend you using complex to generate better images Note: V1.5 contains a watermark embedded in the model, just like V1 and this is not effect the results of generated images. Moreover, this version may break all LoRAs trained on Anima v1.0, as well as those trained on merged or variant versions based on anima v1.0.