The above tool is a Stable Diffusion Image Variations model that has been fine-tuned to take multiple CLIP image embeddings as inputs, allowing users to combine the image embeddings from multiple images to mix their concepts and add text concepts for greater variation. The output is a 640x640 image and it can be run locally or on Lambda GPU Cloud.
Accès 416,20M Modèle De Prix
Accès 4,96K Modèle De Prix
Accès 0 Modèle De Prix Free