Rmokady
Rank:Average Model Cost: $0.0003
Number of Runs: 1,305,804
Models by this creator
clip_prefix_caption
The clip_prefix_caption model is an image captioning model that combines the CLIP and GPT-2 models. CLIP is used to encode the input image and generate textual representations, which are then used as prefixes for generating captions using GPT-2. This model is useful for generating simple captions for images, and can be a starting point for more complex image captioning models.
$0.001/run
1.3M
Replicate
clip_​prefix_​caption
$-/run
0
Replicate