Emu3
Collection
5 items
β’
Updated
β’
65
| Project Page | Paper | π€HF Models | github | Demo |
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 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.
import os
import os.path as osp
from PIL import Image
import torch
from transformers import AutoModel, AutoImageProcessor
MODEL_HUB = "BAAI/Emu3-VisionTokenizer"
model = AutoModel.from_pretrained(MODEL_HUB, trust_remote_code=True).eval().cuda()
processor = AutoImageProcessor.from_pretrained(MODEL_HUB, trust_remote_code=True)
# TODO: you need to modify the path here
VIDEO_FRAMES_PATH = "YOUR_VIDEO_FRAMES_PATH"
video = os.listdir(VIDEO_FRAMES_PATH)
video.sort()
video = [Image.open(osp.join(VIDEO_FRAMES_PATH, v)) for v in video]
images = processor(video, return_tensors="pt")["pixel_values"]
images = images.unsqueeze(0).cuda()
# image autoencode
image = images[:, 0]
print(image.shape)
with torch.no_grad():
# encode
codes = model.encode(image)
# decode
recon = model.decode(codes)
recon = recon.view(-1, *recon.shape[2:])
recon_image = processor.postprocess(recon)["pixel_values"][0]
recon_image.save("recon_image.png")
# video autoencode
images = images.view(
-1,
model.config.temporal_downsample_factor,
*images.shape[2:],
)
print(images.shape)
with torch.no_grad():
# encode
codes = model.encode(images)
# decode
recon = model.decode(codes)
recon = recon.view(-1, *recon.shape[2:])
recon_images = processor.postprocess(recon)["pixel_values"]
for idx, im in enumerate(recon_images):
im.save(f"recon_video_{idx}.png")