NEWVectors or files. Pick a path.Start →
    Runs as a custom pluginEmbeddingVerified 2026-11-05

    FashionCLIP (2.0)

    patrickjohncyh/fashion-clip

    FashionCLIP (2.0) is a image and text embedding model (MIT). Can run on Mixpeek as a custom plugin.

    Mixpeek does not run it today. It can run as a custom plugin: the weights load without remote code.

    Record as JSON

    No demo for FashionCLIP (2.0) yet

    A video, image, slideshow or playground goes here once we record one on our own data.

    What it is good and bad at

    Best at
    Product attributes in fashion catalogs: garment type, color, pattern, material, style words.
    Worst at
    General scenes, people in context, and anything outside apparel; English only.
    Task
    Embedding
    Input
    Image, Text
    Output
    Vector
    Use cases
    Fashion, Product search, Visual search

    Templates that use it

    No template uses this model yet. Browse templates.

    Input and output

    Input

    image
    resolution
    224x224
    color
    RGB
    normalize
    CLIP mean (0.4815, 0.4578, 0.4082), std (0.2686, 0.2613, 0.2758)
    text
    max_tokens
    77
    prompts
    product-style captions, e.g. 'a red midi dress with floral print'

    Output

    vector
    dims
    512
    distance
    cosine
    type
    dense
    note
    image and text vectors share one space; L2-normalize before cosine

    How Mixpeek wires it

    Extractors
    None today
    Feature URIs
    None today
    Vector indexes
    None
    Retriever stages
    feature_search, mmr
    Combines with
    • product images -> FashionCLIP vectors -> feature_search with attribute filters on price and brand
    • detector person boxes -> garment crops -> FashionCLIP vectors

    How it runs

    Status
    Runs as a custom plugin Not served. Would run as a custom extractor plugin (engine/extractors/<name>/v1/ with realtime.py for query embedding), loading safetensors with trust_remote_code false.
    Serve apps
    None
    Runtime
    transformers CLIPModel + CLIPProcessor (ViT-B/32 backbone, LAION base for 2.0)
    Weights
    safetensors, no remote code
    Parameters
    151 M
    Size on disk
    605 MB
    Preprocessing
    Resize and center-crop to 224, CLIP mean/std; text to 77 tokens.
    Postprocessing
    L2-normalize; cosine similarity.
    Serving
    both, batch 32
    Hardware
    Runs on CPU (slower without a GPU)

    Scale to zero

    Minimum replicas
    0
    Maximum replicas
    1
    Idle timeout
    600 s
    Memory
    2 GB
    CPUs
    1
    GPUs
    0
    Cold start, node warm
    Not recorded
    Cold start, new node
    Not recorded

    Measured cost

    Unmeasured

    No committed measurement; plan row 3 measures it in the standalone image.

    Our evaluations

    Unmeasured

    We have not evaluated this model on our own data yet. Publisher results are in the sources below.

    Questions

    What is FashionCLIP (2.0) best at?
    Product attributes in fashion catalogs: garment type, color, pattern, material, style words.
    What are the limits of FashionCLIP (2.0)?
    General scenes, people in context, and anything outside apparel; English only.
    Can FashionCLIP (2.0) be used commercially?
    Yes. MIT license on the repo and weights.
    How does FashionCLIP (2.0) run on Mixpeek?
    Not served. Would run as a custom extractor plugin (engine/extractors/<name>/v1/ with realtime.py for query embedding), loading safetensors with trust_remote_code false.
    What does FashionCLIP (2.0) output?
    A 512-dimensional dense vector, compared by cosine similarity.