Ovis2.6-80B-A3B

pip install torch==2.7.1 transformers==4.57.0 numpy==1.25.0 pillow==10.3.0 moviepy==1.0.3 accelerate==1.12.0
pip install --no-build-isolation --no-cache-dir flash-attn==2.8.3

import torch
import requests
from PIL import Image
from transformers import AutoModelForCausalLM

# Thinking mode & budget
enable_thinking = True
enable_thinking_budget = True  # Only effective if enable_thinking is True.

# Total tokens for thinking + answer. Ensure: max_new_tokens > thinking_budget + 25
max_new_tokens = 2048
thinking_budget = 1024

model = AutoModelForCausalLM.from_pretrained(
    "AIDC-AI/Ovis2.6-80B-A3B",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto"
)

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": Image.open(requests.get("https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png", stream=True).raw)},
        {"type": "text", "text": "Calculate the sum of the numbers in the middle box in figure (c)."},
    ],
}]

input_ids, pixel_values, grid_thws = model.preprocess_inputs(
    messages=messages,
    add_generation_prompt=True,
    enable_thinking=enable_thinking
)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda() if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None

outputs = model.generate(
    inputs=input_ids,
    pixel_values=pixel_values,
    grid_thws=grid_thws,
    enable_thinking=enable_thinking,
    enable_thinking_budget=enable_thinking_budget,
    max_new_tokens=max_new_tokens,
    thinking_budget=thinking_budget,
)

response = model.text_tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

End your response with 'Final answer: '.

Calculate the sum of the numbers in the middle box in figure (c).
End your response with 'Final answer: '.

# --- Budget-aware streamer helper ---
from transformers import TextIteratorStreamer

class BudgetAwareTextStreamer(TextIteratorStreamer):
    """A streamer compatible with Ovis two-phase generation.

    Call .manual_end() after generation to flush any remaining text.
    """
    def manual_end(self):
        if len(self.token_cache) > 0:
            text = self.tokenizer.decode(self.token_cache, **self.decode_kwargs)
            printable_text = text[self.print_len:]
            self.token_cache = []
            self.print_len = 0
        else:
            printable_text = ""
        self.next_tokens_are_prompt = True
        self.on_finalized_text(printable_text, stream_end=True)

    # Disable base class's end hook; we'll finalize via manual_end()
    def end(self):
        pass

streamer = BudgetAwareTextStreamer(
    model.text_tokenizer,
    skip_prompt=True,
    skip_special_tokens=True
)

outputs = model.generate(
    inputs=input_ids,
    pixel_values=pixel_values,
    grid_thws=grid_thws,
    enable_thinking=enable_thinking,
    enable_thinking_budget=enable_thinking_budget,
    max_new_tokens=max_new_tokens,
    thinking_budget=thinking_budget,
    streamer=streamer
)

# Multi-image inference
multi_image_files = [
    "/path/to/image_1.jpg",
    "/path/to/image_2.jpg",
    "/path/to/image_3.jpg",
]

content = [{"type": "image", "image": Image.open(p).convert("RGB")} for p in multi_image_files]
content.append({"type": "text", "text": "Describe the images."})
messages = [{"role": "user", "content": content}]

input_ids, pixel_values, grid_thws = model.preprocess_inputs(messages=messages, add_generation_prompt=True, max_pixels=896*896)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda().to(model.dtype) if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None

with torch.no_grad():
    outputs = model.generate(inputs=input_ids, pixel_values=pixel_values, grid_thws=grid_thws,
                             max_new_tokens=1024, do_sample=True,
                             eos_token_id=model.text_tokenizer.eos_token_id,
                             pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))

# Video inference
from moviepy.editor import VideoFileClip  # pip install moviepy==1.0.3

video_file = "/path/to/video_1.mp4"
num_frames = 8

with VideoFileClip(video_file) as clip:
    total_frames = int(clip.fps * clip.duration)
    indices = [int(i * total_frames / num_frames) for i in range(num_frames)]
    frames = [Image.fromarray(clip.get_frame(t)) for t in (idx / clip.fps for idx in indices)]

messages = [{"role": "user", "content": [
    {"type": "video", "video": frames},
    {"type": "text", "text": "Describe this video in detail."},
]}]

input_ids, pixel_values, grid_thws = model.preprocess_inputs(messages=messages, add_generation_prompt=True, max_pixels=896*896)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda().to(model.dtype) if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None

with torch.no_grad():
    outputs = model.generate(inputs=input_ids, pixel_values=pixel_values, grid_thws=grid_thws,
                             max_new_tokens=1024, do_sample=True,
                             eos_token_id=model.text_tokenizer.eos_token_id,
                             pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))

# Text-only inference
messages = [{"role": "user", "content": "Hi, please introduce Yellow Mountain."}]

input_ids, _, _ = model.preprocess_inputs(messages=messages, add_generation_prompt=True)
input_ids = input_ids.cuda()

with torch.no_grad():
    outputs = model.generate(inputs=input_ids, max_new_tokens=1024, do_sample=True,
                             eos_token_id=model.text_tokenizer.eos_token_id,
                             pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))

Find the <ref>red apple</ref> in the image. Please provide the bounding box coordinates.

The image features a serene scene with <ref>three birds</ref>[
  <box>(0.401,0.526),(0.430,0.557)</box>,
  <box>(0.489,0.494),(0.516,0.526)</box>,
  <box>(0.296,0.529),(0.324,0.576)</box>
] flying in formation against a clear blue sky.

@article{lu2025ovis25technicalreport,
  title={Ovis2.5 Technical Report}, 
  author={Shiyin Lu and Yang Li and Yu Xia and Yuwei Hu and Shanshan Zhao and Yanqing Ma and Zhichao Wei and Yinglun Li and Lunhao Duan and Jianshan Zhao and Yuxuan Han and Haijun Li and Wanying Chen and Junke Tang and Chengkun Hou and Zhixing Du and Tianli Zhou and Wenjie Zhang and Huping Ding and Jiahe Li and Wen Li and Gui Hu and Yiliang Gu and Siran Yang and Jiamang Wang and Hailong Sun and Yibo Wang and Hui Sun and Jinlong Huang and Yuping He and Shengze Shi and Weihong Zhang and Guodong Zheng and Junpeng Jiang and Sensen Gao and Yi-Feng Wu and Sijia Chen and Yuhui Chen and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang},
  year={2025},
  journal={arXiv:2508.11737}
}

@article{lu2024ovis,
  title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
  author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
  year={2024},
  journal={arXiv:2405.20797}
}