novaAnimeXL_ilV140 is a text-to-image model published on Hugging Face by user frankjoshua. It belongs to the class of Stable Diffusion XL models and is provided in Safetensors format with 3 billion parameters using F16 tensor type.
The model implements the StableDiffusionXLPipeline from the Diffusers library. Code examples show it loading via DiffusionPipeline.from_pretrained with bfloat16 precision and CUDA device mapping, then generating an image from a text prompt such as "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k". It records 168902 downloads in the last month.
Usage instructions cover integration through the Diffusers library along with transformers and accelerate. Notebooks for Google Colab and Kaggle are referenced, as are local applications Draw Things and DiffusionBee. No model card text supplies further details on training, intended audience, or specific anime capabilities.
The repository lists the model under the Text-to-Image task. It is not deployed by any Inference Provider. No pricing, licensing terms, or additional platform support appear in the available information.
novaAnimeXL Il is an Image generation product. It focuses on generating high-quality anime-style images from text prompts using a specialized diffusion model. It is built as an open-source project for digital artists and anime content creators. novaAnimeXL Il is open source under the Open Source license. novaAnimeXL Il is available on the web, the command line, and API.
frankjoshua builds and maintains novaAnimeXL Il, and the product first shipped in 2024. Key capabilities include Text-to-Image Generation, Anime Style, and Stable Diffusion XL. It exposes integrations via a public API.
Latest indexed changes and source events
frankjoshua/novaAnimeXL_ilV140 verified by the PulseGate indexer
Other apps tracked under the same category.
