Saltar al contenido
ModelPublicadoExterno
Descargar

Ccip Anime Character Id

CCIP enables determining whether two images depict the same character, calculating visual similarity between characters.

Fuentehuggingface.co/nebulette/ccip-anime-character-id/tree/2c45301b74fe07a86178a064042d31f41ffed3e6
TipoOtherVersiónModelCcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
36,4 MB
Versión
vModel
Actualizado
10 oct 2026
Fuente
Hugging Face

Descripción de la fuente

Character similarity between images

CCIP enables determining whether two images depict the same character, calculating visual similarity between characters.

There are up to 6000 (female) characters available.

The model assigns a score to each image patch to make the features distinguishable on a 2D plane.

The cosine similarity between the scores of two images is used to identify the same characters in both.

The takeaway is that the model doesn't need a tokenizer, text model, or cross-attention. The labels are unknown to the model during training.

Source data

  • live gelbooru feed
  • character_index
  • character_similarity

References

  • Yann LeCun's $1B Bet Against LLMs [Welch Labs]

Fuentes

1 fuente
Hugging FacePrincipalVersión 2c45301b74fe07a86178a064042d31f41ffed3e6
huggingface.co/nebulette/ccip-anime-character-id/tree/2c45301b74fe07a86178a064042d31f41ffed3e6

Verificado 10 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 36,4 MB · SHA-256 4b9a3efa3df4…c88e · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme1 agohuggingface.co/nebulette/ccip-anime-character-id

--- license: apache-2.0 tags: - anime-tagger - character pipeline_tag: image-feature-extraction --- Character similarity between images CCIP enables determining whether two images depict the same character, calculating visual similarity between characters. There are up to 6000 (female) characters available. The model assigns a score to each image patch to make the features distinguishable on a 2D plane. ![](images/bell_shape.png) The cosine similarity between the scores of two images is used to identify the same characters in both. The takeaway is that the model doesn't need a tokenizer, text model, or cross-attention. The labels are unknown to the model during training. Source data - live gelbooru feed - character_index - character_similarity References - Yann LeCun's $1B Bet Against LLMs [Welch Labs]

Note1 agohuggingface.co/nebulette/ccip-anime-character-id

Source context: 0 downloads · 0 likes · Pipeline image-feature-extraction · Repo nebulette/ccip-anime-character-id