lmms-lab-encoder/onevision-encoder-large

from transformers import AutoModel, AutoImageProcessor
from PIL import Image
import torch

# Load model and preprocessor
model = AutoModel.from_pretrained(
    "lmms-lab-encoder/onevision-encoder-large",
    trust_remote_code=True,
    attn_implementation="flash_attention_2"
).to("cuda").eval()

preprocessor = AutoImageProcessor.from_pretrained(
    "lmms-lab-encoder/onevision-encoder-large",
    trust_remote_code=True
)

# Image inference: [B, C, H, W]
image = Image.open("path/to/your/image.jpg")  # Replace with your image path
pixel_values = preprocessor(images=image, return_tensors="pt")["pixel_values"].to("cuda")
with torch.no_grad():
    outputs = model(pixel_values)
    # outputs.last_hidden_state: [B, num_patches, hidden_size]
    # outputs.pooler_output: [B, hidden_size]

# Video inference: [B, C, T, H, W] with patch_positions
num_frames, target_frames = 16, 64
patch_size = 14
# Load video frames and preprocess each frame (replace with your video frame paths)
frames = [Image.open(f"path/to/frame_{i}.jpg") for i in range(num_frames)]
video_pixel_values = preprocessor(images=frames, return_tensors="pt")["pixel_values"]
# Reshape from [T, C, H, W] to [B, C, T, H, W]
video = video_pixel_values.unsqueeze(0).permute(0, 2, 1, 3, 4).to("cuda")

# Build patch_positions for temporal sampling: [B, num_frames * frame_tokens, 3]
frame_pos = torch.linspace(0, target_frames - 1, num_frames).long().cuda()  # [T]
grid_h, grid_w = video.shape[-2] // patch_size, video.shape[-1] // patch_size  # patch grid
frame_tokens = grid_h * grid_w

t_positions = frame_pos[:, None].repeat(1, frame_tokens).reshape(-1)  # [T * frame_tokens]
h_positions = torch.arange(grid_h, device="cuda").repeat_interleave(grid_w)
h_positions = h_positions.repeat(num_frames)  # [T * frame_tokens]
w_positions = torch.arange(grid_w, device="cuda").repeat(grid_h)
w_positions = w_positions.repeat(num_frames)  # [T * frame_tokens]

patch_positions = torch.stack([t_positions, h_positions, w_positions], dim=-1).unsqueeze(0)
# patch_positions example (256 tokens per frame, 16x16 patch grid):
#   Each row is [t, h, w].
#   First 4 patches of frame 0 (t=0):
#     patch_positions[0, 0:4, :] -> [[0, 0, 0], [0, 0, 1], [0, 0, 2], [0, 0, 3]]
#   First 4 patches of frame 1 (t=4):
#     patch_positions[0, 256:260, :] -> [[4, 0, 0], [4, 0, 1], [4, 0, 2], [4, 0, 3]]

with torch.no_grad():
  outputs = model(video, patch_positions=patch_positions)

git clone https://github.com/EvolvingLMMs-Lab/OneVision-Encoder.git
cd OneVision-Encoder
pip install -e .

from onevision_encoder import OneVisionEncoderModel, OneVisionEncoderConfig
from transformers import AutoImageProcessor
model = OneVisionEncoderModel.from_pretrained(
    "lmms-lab-encoder/onevision-encoder-large",
    trust_remote_code=True,
    attn_implementation="flash_attention_2"
).to("cuda").eval()
preprocessor = AutoImageProcessor.from_pretrained(
    "lmms-lab-encoder/onevision-encoder-large",
    trust_remote_code=True
)