Average Model Cost: $0.0154
Number of Runs: 466,470
Models by this creator
The LoRA model trainer is a machine learning model that specializes in image-to-image translation. It is trained to convert images from one category to another, such as changing a face to a different style or transforming objects. The model offers different presets for faces, objects, and styles, making it easier to use for various applications.
The fad_v0_lora model is an image-to-image model that employs the usage of LoRA and Foto-Assisted-Diffusion-FAD_V0. The model's input schema involves several parameters including width, height, a narrative prompt, a scheduler, the number of outputs, a guidance scale and the number of inference steps. Using these inputs, it generates an image described by the prompt and outputs a URL link to this image. For instance, in the provided description, it could render an image depicting "a man riding his bike down the city streets of Japan, magic hour".
The PortraitPlus model is a text-to-image model that generates realistic portraits based on textual descriptions. It takes a textual description as input and generates an image that represents the described portrait. This model can be useful in various applications such as generating visual representations for characters in books or creating custom avatars based on user descriptions.
The vintedois_lora model is a text-to-image generation model. It takes a textual description as input and generates a corresponding image. The model uses the LoRA architecture and operates at half-precision (fp16) to balance performance and accuracy. This version of the model is v0-1 of the diffusion version.