rmokady/CLIP_prefix_caption

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1423 stars · 225 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official implementation of ClipCap, a CLIP-based image captioning model that maps CLIP image encodings to a GPT-2 prefix to generate captions. It requires only images and captions for training and achieves near state-of-the-art results with fast training.

Use cases

• generate captions for images automatically
• caption photos without object annotations
• fine-tune an image captioning model on my own image-caption dataset
• describe images with a pretrained vision-language model
• reproduce ClipCap paper results on COCO or Conceptual Captions
• add image-to-text captioning to a Python project

When to choose

• you need image captioning without extra object-annotation supervision
• you want a lightweight, fast-training captioning model
• you want to build on CLIP embeddings for image-to-text generation
• you want a Colab-ready inference notebook

Facets

library · maturity maintenance

machine-learning deep-learning nlp computer-vision image-processing machine-learning computer-vision deep-learning python image-captioning clip gpt-2 clipcap research-code jupyter-notebook natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rmokady/CLIP_prefix_caption")