Janus/README.md

<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<!-- markdownlint-disable no-duplicate-header -->

<div align="center">
  <img src="images/logo.svg" width="60%" alt="DeepSeek LLM" />
</div>
<hr>
<div align="center">

  <a href="https://www.deepseek.com/" target="_blank">
    <img alt="Homepage" src="images/badge.svg" />
  </a>
  </a>
  <a href="https://huggingface.co/deepseek-ai" target="_blank">
    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" />
  </a>

</div>


<div align="center">

  <!-- <a href="https://discord.gg/Tc7c45Zzu5" target="_blank">
    <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" />
  </a> -->
  <!-- <a href="images/qr.jpeg" target="_blank">
    <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" />
  </a> -->
  <!-- <a href="https://twitter.com/deepseek_ai" target="_blank">
    <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" />
  </a> -->

</div>

<div align="center">

  <a href="LICENSE-CODE">
    <img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53">
  </a>
  <a href="LICENSE-MODEL">
    <img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53">
  </a>
</div>


<p align="center">
  <a href="#2-model-download"><b>📥 Model Download</b></a> |
  <a href="#3-quick-start"><b>⚡ Quick Start</b></a> |
  <a href="#4-license"><b>📜 License</b></a> |
  <a href="#5-citation"><b>📖 Citation</b></a> <br>
  <a href="https://arxiv.org/abs/2410.13848"><b>📄 Paper Link</b></a> |
</p>


## 1. Introduction

Janus is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. Janus surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models.

<div align="center">
<img alt="image" src="images/teaser.png" style="width:90%;">
</div>


## 2. Model Download

We release Janus to the public to support a broader and more diverse range of research within both academic and commercial communities.
Please note that the use of this model is subject to the terms outlined in [License section](#4-license). Commercial usage is
permitted under these terms.

### Huggingface

| Model                 | Sequence Length | Download                                                                    |
|-----------------------|-----------------|-----------------------------------------------------------------------------|
| Janus-1.3B | 4096            | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/Janus-1.3B) |




## 3. Quick Start

### Installation

On the basis of `Python >= 3.8` environment, install the necessary dependencies by running the following command:

```shell
pip install -e .
```

### Simple Inference Example

#### Multimodal Understanding
```python

import torch
from transformers import AutoModelForCausalLM
from janus.models import MultiModalityCausalLM, VLChatProcessor
from janus.utils.io import load_pil_images

# specify the path to the model
model_path = "deepseek-ai/Janus-1.3B"
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer

vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(
    model_path, trust_remote_code=True
)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()

conversation = [
    {
        "role": "User",
        "content": "<image_placeholder>\nConvert the formula into latex code.",
        "images": ["images/equation.png"],
    },
    {"role": "Assistant", "content": ""},
]

# load images and prepare for inputs
pil_images = load_pil_images(conversation)
prepare_inputs = vl_chat_processor(
    conversations=conversation, images=pil_images, force_batchify=True
).to(vl_gpt.device)

# # run image encoder to get the image embeddings
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)

# # run the model to get the response
outputs = vl_gpt.language_model.generate(
    inputs_embeds=inputs_embeds,
    attention_mask=prepare_inputs.attention_mask,
    pad_token_id=tokenizer.eos_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=512,
    do_sample=False,
    use_cache=True,
)

answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
print(f"{prepare_inputs['sft_format'][0]}", answer)

```

#### Text-to-Image Generation
```python
import os
import PIL.Image
import torch
import numpy as np
from transformers import AutoModelForCausalLM
from janus.models import MultiModalityCausalLM, VLChatProcessor


# specify the path to the model
model_path = "deepseek-ai/Janus-1.3B"
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer

vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(
    model_path, trust_remote_code=True
)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()

conversation = [
    {
        "role": "User",
        "content": "A stunning princess from kabul in red, white traditional clothing, blue eyes, brown hair",
    },
    {"role": "Assistant", "content": ""},
]

sft_format = vl_chat_processor.apply_sft_template_for_multi_turn_prompts(
    conversations=conversation,
    sft_format=vl_chat_processor.sft_format,
    system_prompt="",
)
prompt = sft_format + vl_chat_processor.image_start_tag


@torch.inference_mode()
def generate(
    mmgpt: MultiModalityCausalLM,
    vl_chat_processor: VLChatProcessor,
    prompt: str,
    temperature: float = 1,
    parallel_size: int = 16,
    cfg_weight: float = 5,
    image_token_num_per_image: int = 576,
    img_size: int = 384,
    patch_size: int = 16,
):
    input_ids = vl_chat_processor.tokenizer.encode(prompt)
    input_ids = torch.LongTensor(input_ids)

    tokens = torch.zeros((parallel_size*2, len(input_ids)), dtype=torch.int).cuda()
    for i in range(parallel_size*2):
        tokens[i, :] = input_ids
        if i % 2 != 0:
            tokens[i, 1:-1] = vl_chat_processor.pad_id

    inputs_embeds = mmgpt.language_model.get_input_embeddings()(tokens)

    generated_tokens = torch.zeros((parallel_size, image_token_num_per_image), dtype=torch.int).cuda()

    for i in range(image_token_num_per_image):
        outputs = mmgpt.language_model.model(inputs_embeds=inputs_embeds, use_cache=True, past_key_values=outputs.past_key_values if i != 0 else None)
        hidden_states = outputs.last_hidden_state
        
        logits = mmgpt.gen_head(hidden_states[:, -1, :])
        logit_cond = logits[0::2, :]
        logit_uncond = logits[1::2, :]
        
        logits = logit_uncond + cfg_weight * (logit_cond-logit_uncond)
        probs = torch.softmax(logits / temperature, dim=-1)

        next_token = torch.multinomial(probs, num_samples=1)
        generated_tokens[:, i] = next_token.squeeze(dim=-1)

        next_token = torch.cat([next_token.unsqueeze(dim=1), next_token.unsqueeze(dim=1)], dim=1).view(-1)
        img_embeds = mmgpt.prepare_gen_img_embeds(next_token)
        inputs_embeds = img_embeds.unsqueeze(dim=1)


    dec = mmgpt.gen_vision_model.decode_code(generated_tokens.to(dtype=torch.int), shape=[parallel_size, 8, img_size//patch_size, img_size//patch_size])
    dec = dec.to(torch.float32).cpu().numpy().transpose(0, 2, 3, 1)

    dec = np.clip((dec + 1) / 2 * 255, 0, 255)

    visual_img = np.zeros((parallel_size, img_size, img_size, 3), dtype=np.uint8)
    visual_img[:, :, :] = dec

    os.makedirs('generated_samples', exist_ok=True)
    for i in range(parallel_size):
        save_path = os.path.join('generated_samples', "img_{}.jpg".format(i))
        PIL.Image.fromarray(visual_img[i]).save(save_path)


generate(
    vl_gpt,
    vl_chat_processor,
    prompt,
)
```

## 4. License

This code repository is licensed under [the MIT License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-CODE). The use of Janus models is subject to [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL).

## 5. Citation

```
@misc{wu2024janus,
      title={Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation}, 
      author={Chengyue Wu and Xiaokang Chen and Zhiyu Wu and Yiyang Ma and Xingchao Liu and Zizheng Pan and Wen Liu and Zhenda Xie and Xingkai Yu and Chong Ruan and Ping Luo},
      year={2024},
      eprint={2410.13848},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2410.13848}, 
}
```

## 6. Contact

If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).