Runs as a custom pluginEmbeddingVerified 2026-11-05
Marqo-FashionCLIP
Marqo/marqo-fashionCLIP
Marqo-FashionCLIP is a image and text embedding model (Apache-2.0). 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.
No demo for Marqo-FashionCLIP 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
- Fashion product search from text or image (ViT-B/16 CLIP fine-tuned with generalized contrastive learning on product titles, categories and attributes); Marqo reports gains over FashionCLIP 2.0 on its fashion benchmarks.
- Worst at
- Non-fashion content; the transformers path needs remote code (use open_clip instead).
- 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 titles and attributes
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 -> vectors -> feature_search; attributes as filters
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. Load through open_clip ('hf-hub:Marqo/marqo-fashionCLIP', open_clip_model.safetensors); the repo's transformers path is custom code and is not used.
- Serve apps
- None
- Runtime
- open_clip create_model_and_transforms('hf-hub:<id>')
- Weights
- safetensors, no remote code
- Parameters
- 150 M
- Size on disk
- 599 MB
- Preprocessing
- open_clip preprocess for the checkpoint (resize, center-crop 224, normalize).
- 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 Marqo-FashionCLIP best at?
- Fashion product search from text or image (ViT-B/16 CLIP fine-tuned with generalized contrastive learning on product titles, categories and attributes); Marqo reports gains over FashionCLIP 2.0 on its fashion benchmarks.
- What are the limits of Marqo-FashionCLIP?
- Non-fashion content; the transformers path needs remote code (use open_clip instead).
- Can Marqo-FashionCLIP be used commercially?
- Yes. Apache-2.0 weights and code; no use restrictions.
- How does Marqo-FashionCLIP 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. Load through open_clip ('hf-hub:Marqo/marqo-fashionCLIP', open_clip_model.safetensors); the repo's transformers path is custom code and is not used.
- What does Marqo-FashionCLIP output?
- A 512-dimensional dense vector, compared by cosine similarity.