Coreml Stable Diffusion V1 5

Coreml Stable Diffusion V1 5 is a model based on Stable Diffusion v1-5, designed for text-to-image generation. The model is available on Hugging Face and was generated using Apple's repository. It is described as a latent text-to-image diffusion model that can create photo-realistic images from any text input. The checkpoint for this version was initialized with weights from the Stable-Diffusion-v1-2 checkpoint and then fine-tuned for 595,000 steps at a resolution of 512x512 on the "laion-aesthetics v2 5+" dataset, with 10% of the text-conditioning dropped to improve classification. The model is compatible with Core ML, as indicated by its naming and the connection to Apple's repository, though specific details about deployment or required hardware are not stated in the provided evidence. The licensing is listed as "other," and there is no additional information about pricing or specific user groups. The evidence does not provide further details on features, integrations, or supported platforms beyond its Core ML compatibility and text-to-image functionality.