---
license: apache-2.0
base_model:
- Lykon/DreamShaper
pipeline_tag: text-to-image
---
# TDM: Learning Few-Step Diffusion Models by Trajectory Distribution Matching
This is the Official Repository of "[Learning Few-Step Diffusion Models by Trajectory Distribution Matching](https://arxiv.org/abs/2503.06674)", by *Yihong Luo, Tianyang Hu, Jiacheng Sun, Yujun Cai, Jing Tang*.
## User Study Time!
Which one do you think is better? Some images are generated by Pixart-α (50 NFE). Some images are generated by **TDM (4 NFE)**, distilling from Pixart-α in a data-free way with merely 500 training iterations and 2 A800 hours.
Click for answer
Answers of TDM's position (left to right): bottom, bottom, top, bottom, top.
## Fast Text-to-Video Geneartion
Our proposed TDM can be easily extended to text-to-video.
The video on the above was generated by CogVideoX-2B (100 NFE). In the same amount of time, **TDM (4NFE)** can generate 25 videos, as shown in the below, achieving an impressive **25 times speedup without performance degradation**. (Note: The noise in the GIF is due to compression.)
## Usage
### TDM-SD3-LoRA
```python
import torch
from diffusers import StableDiffusion3Pipeline, AutoencoderTiny, DPMSolverMultistepScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from diffusers.utils import make_image_grid
pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights('Luo-Yihong/TDM_sd3_lora', adapter_name = 'tdm') # Load TDM-LoRA
pipe.set_adapters(["tdm"], [0.125])# IMPORTANT. Please set LoRA scale to 0.125.
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16) # Save GPU memory.
pipe.vae.config.shift_factor = 0.0
pipe = pipe.to("cuda")
pipe.scheduler = DPMSolverMultistepScheduler.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", subfolder="scheduler")
pipe.scheduler.config['flow_shift'] = 6 # the flow_shift can be changed from 1 to 6.
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
generator = torch.manual_seed(8888)
image = pipe(
prompt="A cute panda holding a sign says TDM SOTA!",
negative_prompt="",
num_inference_steps=4,
height=1024,
width=1024,
num_images_per_prompt = 1,
guidance_scale=1.,
generator = generator,
).images[0]
pipe.scheduler = DPMSolverMultistepScheduler.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", subfolder="scheduler")
pipe.set_adapters(["tdm"], [0.]) # Unload lora
generator = torch.manual_seed(8888)
teacher_image = pipe(
prompt="A cute panda holding a sign says TDM SOTA!",
negative_prompt="",
num_inference_steps=28,
height=1024,
width=1024,
num_images_per_prompt = 1,
guidance_scale=7.,
generator = generator,
).images[0]
make_image_grid([image,teacher_image],1,2)
```
The sample generated by SD3 with 56 NFE is on the right, and the sample generated by **TDM** with 4NFE is on the left. Which one do you feel is better?
### TDM-Dreamshaper-v7-LoRA
```python
import torch
from diffusers import DiffusionPipeline, UNet2DConditionModel, DPMSolverMultistepScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
repo_name = "Luo-Yihong/TDM_dreamshaper_LoRA"
ckpt_name = "tdm_dreamshaper.pt"
pipe = DiffusionPipeline.from_pretrained('lykon/dreamshaper-7', torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.scheduler = DPMSolverMultistepScheduler.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="scheduler")
generator = torch.manual_seed(317)
image = pipe(
prompt="A close-up photo of an Asian lady with sunglasses",
negative_prompt="",
num_inference_steps=4,
num_images_per_prompt = 1,
generator = generator,
guidance_scale=1.,
).images[0]
image
```
## TDM-CogVideoX-2B-LoRA
```python
import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video
pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b", torch_dtype=torch.float16)
pipe.vae.enable_slicing() # Save memory
pipe.vae.enable_tiling() # Save memory
pipe.load_lora_weights("Luo-Yihong/TDM_CogVideoX-2B_LoRA")
pipe.to("cuda")
prompt = (
"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The "
"panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other "
"pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, "
"casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. "
"The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical "
"atmosphere of this unique musical performance"
)
# We train the generator on timesteps [999, 856, 665, 399].
# The official scheduler of CogVideo-X using uniform spacing, may cause inferior results.
# But TDM-LoRA still works well under 4 NFE.
# We will update the TDM-CogVideoX-LoRA soon for better performance!
generator = torch.manual_seed(8888)
frames = pipe(prompt, guidance_scale=1,
num_inference_steps=4,
num_frames=49,
generator = generator,
use_dynamic_cfg=True).frames[0]
export_to_video(frames, "output-TDM.mp4", fps=8)
```
## 🔥 Pre-trained Models
We release a bucket of TDM-LoRA. Please enjoy it!
- [TDM-SD3-LoRA](https://huggingface.co/Luo-Yihong/TDM_sd3_lora)
- [TDM-CogVideoX-2B-LoRA](https://huggingface.co/Luo-Yihong/TDM_CogVideoX-2B_LoRA)
- [TDM-Dreamshaper-LoRA](https://huggingface.co/Luo-Yihong/TDM_dreamshaper_LoRA)
## Contact
Please contact Yihong Luo (yluocg@connect.ust.hk) if you have any questions about this work.
## Bibtex
```
@misc{luo2025tdm,
title={Learning Few-Step Diffusion Models by Trajectory Distribution Matching},
author={Yihong Luo and Tianyang Hu and Jiacheng Sun and Yujun Cai and Jing Tang},
year={2025},
eprint={2503.06674},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.06674},
}
``` 
