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/image_focus.py from Cloudflare/clairic: direct link, hf CLI and curl.
- Browser
- Download file 1.58 kB
-
https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/image_focus.py
- Command line
-
hf download hf://Cloudflare/clairic/clairic_runtime/image_focus.py
-
curl -L -o image_focus.py https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/image_focus.py
1.58 kB
| from __future__ import annotations | |
| from typing import Any | |
| from PIL import Image, ImageChops | |
| COPY_INSTRUCTION = " Copy the complete printed value verbatim, including every digit, punctuation and suffix. Do not shorten, sanitize or canonicalize it." | |
| def preserve_scalar_fields( | |
| fields: dict[str, dict[str, Any]], | |
| ) -> dict[str, dict[str, Any]]: | |
| return { | |
| name: {**spec, "instructions": spec.get("instructions", "") + COPY_INSTRUCTION} | |
| if spec.get("type") == "text" | |
| and (not spec.get("knowledge")) | |
| and isinstance(spec.get("instructions", ""), str) | |
| else spec | |
| for (name, spec) in fields.items() | |
| } | |
| def focus_document( | |
| image: Image.Image, *, max_pixels: int = 1600000, max_scale: float = 2.0 | |
| ) -> Image.Image: | |
| if image.mode != "RGB": | |
| return image | |
| bounds = ImageChops.difference( | |
| image, Image.new("RGB", image.size, "white") | |
| ).getbbox() | |
| if bounds is None: | |
| return image | |
| (left, top, right, bottom) = bounds | |
| bounds = ( | |
| max(0, left - 24), | |
| max(0, top - 24), | |
| min(image.width, right + 24), | |
| min(image.height, bottom + 24), | |
| ) | |
| (width, height) = (bounds[2] - bounds[0], bounds[3] - bounds[1]) | |
| if width * height > image.width * image.height / 2: | |
| return image | |
| scale = min(max_scale, (max_pixels / (width * height)) ** 0.5) | |
| if scale <= 1: | |
| return image | |
| focused = image.crop(bounds) | |
| return focused.resize( | |
| (max(1, int(width * scale)), max(1, int(height * scale))), | |
| Image.Resampling.BICUBIC, | |
| ) | |