Not runnable todayEmbeddingVerified 2026-11-05
OpenCLIP ViT-B/16 DataComp-1B
laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K
OpenCLIP ViT-B/16 DataComp-1B is a image and text embedding model (MIT). Not runnable on Mixpeek today.
Something blocks it today, such as the license, remote code or a GPU-only runtime. The reason is below.
No demo for OpenCLIP ViT-B/16 DataComp-1B 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
- Strong B/16 trained on the filtered DataComp-1B set.
- Worst at
- English-centric text tower (77 tokens); weak on text in images and counting.
- Task
- Embedding
- Input
- Image, Text
- Output
- Vector
- Use cases
- Visual search, Product 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
- 'a photo of a {label}.'; open_clip tokenizer, 77 tokens
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
- video frames (VideoFrameExpander) -> image vectors -> feature_search with a text query
- detector boxes (RT-DETR, D-FINE) -> crops -> image vectors per object
- image vectors + E5 text vectors on captions -> feature_search fusion (dbsf)
How it runs
- Status
- Not runnable today Only open_clip_pytorch_model.bin (pickle) on the hub; a plugin needs a one-time safetensors conversion. Otherwise loads with open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K').
- Serve apps
- None
- Runtime
- open_clip create_model_and_transforms('hf-hub:<id>')
- Weights
- Pickle, no remote code
- Parameters
- 150 M
- Size on disk
- 599 MB
- Preprocessing
- Resize and center-crop to 224, CLIP mean/std normalize; tokenize to 77.
- 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 OpenCLIP ViT-B/16 DataComp-1B best at?
- Strong B/16 trained on the filtered DataComp-1B set.
- What are the limits of OpenCLIP ViT-B/16 DataComp-1B?
- English-centric text tower (77 tokens); weak on text in images and counting.
- Can OpenCLIP ViT-B/16 DataComp-1B be used commercially?
- Yes. MIT weights; LAION notes the datasets are for research, the model license itself has no use restriction.
- How does OpenCLIP ViT-B/16 DataComp-1B run on Mixpeek?
- Only open_clip_pytorch_model.bin (pickle) on the hub; a plugin needs a one-time safetensors conversion. Otherwise loads with open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K').
- What does OpenCLIP ViT-B/16 DataComp-1B output?
- A 512-dimensional dense vector, compared by cosine similarity.