Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Paper โข 2405.08748 โข Published โข 23
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
ๆททๅ -DiT: ๅ ทๆ็ป็ฒๅบฆไธญๆ็่งฃ็ๅคๅ่พจ็Diffusion Transformer
[Arxiv] [project page] [github]
This repo contains the pre-trained text-to-image model in ๐ค Diffusers format.
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 ๐ค Diffusers with pip:
pip install git+https://github.com/huggingface/diffusers.git
Example Usage with ๐ค Diffusers
import torch
from diffusers import HunyuanDiTPipeline
pipe = HunyuanDiTPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-Diffusers", 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 = "ไธไธชๅฎ่ชๅๅจ้ช้ฉฌ"
image = pipe(prompt).images[0]
๐ 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 | โ | 64.3 | 60.6 | 91.1 | 76.3 | 42.7 |
| PixArt-ฮฑ | โ | 68.3 | 60.9 | 93.2 | 77.5 | 45.5 |
| Playground 2.5 | โ | 71.9 | 70.8 | 94.9 | 83.3 | 54.3 |
| SD 3 | โ | 77.1 | 69.3 | 94.6 | 82.5 | 56.7 |
| MidJourney v6 | โ | 73.5 | 80.2 | 93.5 | 87.2 | 63.3 |
| DALL-E 3 | โ | 83.9 | 80.3 | 96.5 | 89.4 | 71.0 |
| Hunyuan-DiT | โ | 74.2 | 74.3 | 95.4 | 86.6 | 59.0 |
๐ฅ Visualization
Chinese Elements
Long Text Input
๐ฅ๐ฅ๐ฅ Tencent Hunyuan Bot
Welcome to Tencent Hunyuan Bot, where you can explore our innovative products in multi-round conversation!
- Downloads last month
- 550