Image-Text-to-Text
Transformers
Safetensors
qwen3_5
clairic
cloudflare
systemone
multimodal
structured-output
information-extraction
custom-code
conversational
Instructions to use Cloudflare/clairic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cloudflare/clairic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Cloudflare/clairic") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Cloudflare/clairic") model = AutoModelForMultimodalLM.from_pretrained("Cloudflare/clairic", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Cloudflare/clairic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Cloudflare/clairic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Cloudflare/clairic
- SGLang
How to use Cloudflare/clairic with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Cloudflare/clairic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Cloudflare/clairic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use Cloudflare/clairic with Docker Model Runner:
docker model run hf.co/Cloudflare/clairic
Download clairic_runtime/media_cache.py from Cloudflare/clairic: direct link, hf CLI and curl.
- Browser
- Download file 3.52 kB
-
https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/media_cache.py
- Command line
-
hf download hf://Cloudflare/clairic/clairic_runtime/media_cache.py
-
curl -L -o media_cache.py https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/media_cache.py
3.52 kB
| from __future__ import annotations | |
| from collections.abc import Iterable | |
| from typing import TYPE_CHECKING, Any, cast | |
| if TYPE_CHECKING: | |
| from .api import ClairImage | |
| from .documents import ClairDocument | |
| from PIL import Image | |
| from .model import EncodedMedia | |
| import copy | |
| import hashlib | |
| import uuid | |
| from collections import OrderedDict | |
| from dataclasses import dataclass | |
| class PreparedImages: | |
| images: list[Image.Image] | |
| media: EncodedMedia | |
| payload: list[dict[str, Any]] | |
| salt: str | |
| size: int | |
| source_images: list[Image.Image] | None = None | |
| class ImageCache: | |
| _share_image_row_description: bool | |
| def __init__( | |
| self, max_bytes: int = 128 * 1024 * 1024, max_entries: int = 8 | |
| ) -> None: | |
| (self.max_bytes, self.max_entries) = (max_bytes, max_entries) | |
| self.namespace = uuid.uuid4().hex | |
| self.entries: OrderedDict[str, PreparedImages] = OrderedDict() | |
| self.size = 0 | |
| def clear(self) -> None: | |
| self.entries.clear() | |
| self.size = 0 | |
| def key(images: Iterable[ClairImage | ClairDocument]) -> str: | |
| digest = hashlib.sha256() | |
| for image in images: | |
| content = image.base64.encode() | |
| digest.update(getattr(image, "content_type", "image").encode()) | |
| digest.update(str(getattr(image, "rotation", 0)).encode()) | |
| digest.update(bytes(["rotation" in getattr(image, "model_fields_set", ())])) | |
| digest.update(len(content).to_bytes(8, "big")) | |
| digest.update(content) | |
| return digest.hexdigest() | |
| def get(self, key: str) -> PreparedImages | None: | |
| entry = self.entries.get(key) | |
| if entry is not None: | |
| self.entries.move_to_end(key) | |
| return entry | |
| def put( | |
| self, | |
| key: str, | |
| images: list[Image.Image], | |
| media: EncodedMedia, | |
| payload: list[dict[str, Any]], | |
| *, | |
| source_images: list[Image.Image] | None = None, | |
| ) -> PreparedImages: | |
| tensors = {} | |
| for mapping in (cast(dict[str, Any], media.media), *payload): | |
| for value in mapping.values(): | |
| if hasattr(value, "numel"): | |
| tensors[id(value)] = value.numel() * value.element_size() | |
| source_images = images if source_images is None else source_images | |
| retained = {id(image): image for image in [*images, *source_images]} | |
| size = sum(tensors.values()) + sum( | |
| (image.width * image.height * 3 for image in retained.values()) | |
| ) | |
| if ( | |
| media.media | |
| and len(payload) == 1 | |
| and ("pixel_values" in media.media) | |
| and ("pixel_values" in payload[0]) | |
| ): | |
| media = copy.copy(media) | |
| media.media = { | |
| **cast(dict[str, Any], media.media), | |
| "pixel_values": payload[0]["pixel_values"], | |
| } | |
| entry = PreparedImages( | |
| images, media, payload, uuid.uuid4().hex, size, source_images | |
| ) | |
| if size > self.max_bytes: | |
| return entry | |
| old = self.entries.pop(key, None) | |
| if old is not None: | |
| self.size -= old.size | |
| while self.entries and ( | |
| self.size + size > self.max_bytes or len(self.entries) >= self.max_entries | |
| ): | |
| (_, old) = self.entries.popitem(last=False) | |
| self.size -= old.size | |
| self.entries[key] = entry | |
| self.size += size | |
| return entry | |