LibreVLM

1
pip install 'libreyolo[vlm]'

1
from libreyolo import LibreVLM
2
3
# Qwen3-VL-4B by default; weights autodownload on first use
4
model = LibreVLM()
5
6
# The vocabulary is just words. Any words.
7
model.set_classes(["pink car", "wheel"])
8
9
result = model.predict("street.jpg")
10
11
print(result.boxes.xyxy)   # pixel [x1, y1, x2, y2]
12
print(result.boxes.cls)    # ids into ["pink car", "wheel"]
13
result.plot()              # same drawing helpers as any LibreYOLO model
14
result.save("out.jpg")

1
# Sticky and chainable
2
model = LibreVLM("qwen3-vl-2b").set_classes(["person", "dog", "cat"])
3
4
# Set it once at construction instead
5
model = LibreVLM("lfm2-vl-450m", names=["boat"], device="cpu")
6
7
# Re-set any time to change what you are looking for
8
model.set_classes(["a red car", "a blue truck"])

1
result = model.predict(
2
    source="image.jpg",  # path | PIL | ndarray | URL | folder | video
3
    conf=0.25,           # see note below: scoring is synthetic
4
    classes=[0],         # optional: keep only these vocabulary ids
5
    max_det=300,
6
)

1
from libreyolo import LibreVLM
2
3
model = LibreVLM("qwen3-vl-4b")
4
model.set_classes(["red car"])
5
6
result = model.predict("parking_lot.jpg")
7
print(f"Found {len(result.boxes.cls)} red car(s)")
8
result.save("red_cars.jpg")

1
# Florence-2 is a purpose-built grounder: very tight pixel boxes.
2
model = LibreVLM("florence-2-large")
3
model.set_classes(["a red car", "license plate"])
4
5
result = model.predict("car.jpg")
6
result.plot()

1
model = LibreVLM("qwen3-vl-2b").set_classes(["person", "dog", "cat"])
2
3
# classes= filters the configured vocabulary by id
4
people_only = model.predict("street.jpg", classes=[0])

1
from libreyolo import LibreVLM, SAMPLE_IMAGE
2
3
model = LibreVLM("lfm2-vl-450m", device="cpu")
4
# No set_classes() -> falls back to the COCO-80 vocabulary
5
result = model.predict(SAMPLE_IMAGE)
6
print(model.names[result.boxes.cls[0]])  # e.g. "person"

1
model = LibreVLM().set_classes(["forklift", "pallet"])
2
3
# A whole folder
4
for result in model.predict("warehouse_frames/", stream=True):
5
    result.save()
6
7
# A video file (frames are processed one at a time)
8
model.predict("warehouse.mp4", save=True)

1
model = LibreVLM("qwen3-vl-4b")
2
3
answer = model.chat("harbor.jpg", "How many boats are docked? Answer with a number.")
4
print(answer)