🚀 Emu3: Next-Token Prediction is All You Need

We introduce Emu3, a new suite of state - of - the - art multimodal models trained solely with next - token prediction. It excels in both generation and perception tasks, outperforming several well - established models.

🚀 Quick Start

We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.

Emu3 excels in both generation and perception

Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship open models such as SDXL, LLaVA-1.6 and OpenSora-1.2, while eliminating the need for diffusion or compositional architectures.

✨ Features

Highlights

• Emu3 is capable of generating high-quality images following the text input, by simply predicting the next vision token. The model naturally supports flexible resolutions and styles.
• Emu3 shows strong vision-language understanding capabilities to see the physical world and provides coherent text responses. Notably, this capability is achieved without depending on a CLIP and a pretrained LLM.
• Emu3 simply generates a video causally by predicting the next token in a video sequence, unlike the video diffusion model as in Sora. With a video in context, Emu3 can also naturally extend the video and predict what will happen next.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from PIL import Image
from transformers import AutoTokenizer, AutoModel, AutoImageProcessor, AutoModelForCausalLM
from transformers.generation.configuration_utils import GenerationConfig
from transformers.generation import LogitsProcessorList, PrefixConstrainedLogitsProcessor, UnbatchedClassifierFreeGuidanceLogitsProcessor
import torch

import sys
sys.path.append(PATH_TO_BAAI_Emu3-Stage1_MODEL)
from processing_emu3 import Emu3Processor

# model path
EMU_HUB = "BAAI/Emu3-Stage1"
VQ_HUB = "BAAI/Emu3-VisionTokenizer"

# prepare model and processor
model = AutoModelForCausalLM.from_pretrained(
    EMU_HUB,
    device_map="cuda:0",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(EMU_HUB, trust_remote_code=True, padding_side="left")
image_processor = AutoImageProcessor.from_pretrained(VQ_HUB, trust_remote_code=True)
image_tokenizer = AutoModel.from_pretrained(VQ_HUB, device_map="cuda:0", trust_remote_code=True).eval()
processor = Emu3Processor(image_processor, image_tokenizer, tokenizer, chat_template="{image_prompt}{text_prompt}")

# Image Generation
# prepare input
POSITIVE_PROMPT = " masterpiece, film grained, best quality."
NEGATIVE_PROMPT = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry."

classifier_free_guidance = 3.0
prompt = "a portrait of young girl."
prompt += POSITIVE_PROMPT

kwargs = dict(
    mode='G',
    ratio="1:1",
    image_area=model.config.image_area,
    return_tensors="pt",
    padding="longest",
)
pos_inputs = processor(text=prompt, **kwargs)
neg_inputs = processor(text=NEGATIVE_PROMPT, **kwargs)

# prepare hyper parameters
GENERATION_CONFIG = GenerationConfig(
    use_cache=True,
    eos_token_id=model.config.eos_token_id,
    pad_token_id=model.config.pad_token_id,
    max_new_tokens=40960,
    do_sample=True,
    top_k=2048,
)

h = pos_inputs.image_size[:, 0]
w = pos_inputs.image_size[:, 1]
constrained_fn = processor.build_prefix_constrained_fn(h, w)
logits_processor = LogitsProcessorList([
    UnbatchedClassifierFreeGuidanceLogitsProcessor(
        classifier_free_guidance,
        model,
        unconditional_ids=neg_inputs.input_ids.to("cuda:0"),
    ),
    PrefixConstrainedLogitsProcessor(
        constrained_fn ,
        num_beams=1,
    ),
])

# generate
outputs = model.generate(
    pos_inputs.input_ids.to("cuda:0"),
    GENERATION_CONFIG,
    logits_processor=logits_processor,
    attention_mask=pos_inputs.attention_mask.to("cuda:0"),
)

mm_list = processor.decode(outputs[0])
for idx, im in enumerate(mm_list):
    if not isinstance(im, Image.Image):
        continue
    im.save(f"result_{idx}.png")


# Multimodal Understanding
text = "The image depicts "
image = Image.open("assets/demo.png")

inputs = processor(
    text=text,
    image=image,
    mode='U',
    padding="longest",
    return_tensors="pt",
)
GENERATION_CONFIG = GenerationConfig(
    pad_token_id=tokenizer.pad_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=1024,
)

outputs = model.generate(
    inputs.input_ids.to("cuda:0"),
    GENERATION_CONFIG,
    attention_mask=inputs.attention_mask.to("cuda:0"),
)
outputs = outputs[:, inputs.input_ids.shape[-1]:]
answers = processor.batch_decode(outputs, skip_special_tokens=True)
for ans in answers:
    print(ans)

📚 Documentation

Model Information

The Emu3-Stage1 model is the pre-trained weights of the first stage of the pre-training process of Emu3. The pre-training process of Emu3 is conducted in two stages. In the first stage, which does not utilize video data, training begins from scratch with a context length of 5120 for text and image data. The model supports image captioning and can generate images at a resolution of 512x512. You can use our training scripts for further instruction tuning for more image generation and perception tasks.

📄 License

The license of this project is apache-2.0.