Edit model card

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

混元-DiT: 具有细粒度中文理解的多分辨率Diffusion Transformer

[Arxiv] [project page] [github]

This repo contains the distilled Hunyuan-DiT in 🤗 Diffusers format.

It supports 25-step text-to-image generation.

Dependency

Please install PyTorch first, following the instruction in https://pytorch.org

Install the latest version of transformers with pip:

pip install --upgrade transformers

Then install the latest github version of 🤗 Diffusers with pip:

pip install git+https://github.com/huggingface/diffusers.git

Example Usage with 🤗 Diffusers

import torch
from diffusers import HunyuanDiTPipeline

pipe = HunyuanDiTPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers-Distilled", torch_dtype=torch.float16)
pipe.to("cuda")

# You may also use English prompt as HunyuanDiT supports both English and Chinese
# prompt = "An astronaut riding a horse"
prompt = "一个宇航员在骑马"
image = pipe(prompt).images[0]

image/png

📈 Comparisons

In order to comprehensively compare the generation capabilities of HunyuanDiT and other models, we constructed a 4-dimensional test set, including Text-Image Consistency, Excluding AI Artifacts, Subject Clarity, Aesthetic. More than 50 professional evaluators performs the evaluation.

Model Open Source Text-Image Consistency (%) Excluding AI Artifacts (%) Subject Clarity (%) Aesthetics (%) Overall (%)
SDXL ✔ 64.3 60.6 91.1 76.3 42.7
PixArt-α ✔ 68.3 60.9 93.2 77.5 45.5
Playground 2.5 ✔ 71.9 70.8 94.9 83.3 54.3
SD 3 ✘ 77.1 69.3 94.6 82.5 56.7
MidJourney v6✘ 73.5 80.2 93.5 87.2 63.3
DALL-E 3✘ 83.9 80.3 96.5 89.4 71.0
Hunyuan-DiT✔ 74.2 74.3 95.4 86.6 59.0

🎥 Visualization

  • Chinese Elements

  • Long Text Input

🔥🔥🔥 Tencent Hunyuan Bot

Welcome to Tencent Hunyuan Bot, where you can explore our innovative products in multi-round conversation!

Downloads last month
1,748
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.