ModelListedExternal

LightningDiT Diffusers

Diffusers-ready checkpoints for LightningDiT (VA-VAE–aligned latent diffusion with flow matching), converted from hustvl/lightningdit-xl-imagenet256-800ep for local/offline use.

Sourcehuggingface.co/BiliSakura/LightningDiT-diffusers/tree/fdc4fb0d13e20f4ef2148b40e8dae55a4f426779

KindOtherVersiondiffusion_pytorch_modelBgrade

Model source

Kind: Other
File size: 266 MB
Version: vdiffusion_pytorch_model
Updated: Oct 9, 2026
Source: Hugging Face

Source description

LightningDiT-diffusers

Diffusers-ready checkpoints for LightningDiT (VA-VAE–aligned latent diffusion with flow matching), converted from hustvl/lightningdit-xl-imagenet256-800ep for local/offline use.

This root folder is a model collection that contains:

LightningDit-XL-1-256

Each subfolder is a self-contained Diffusers model repo with:

pipeline.py (LightningDiTPipeline)
transformer/transformer_lightningdit.py and weights
scheduler/scheduler_config.json (FlowMatchHeunDiscreteScheduler, shift=0.3)
vae/ (REPA-E/vavae-hf)

Each variant embeds English id2label in model_index.json, so class labels can be passed as ImageNet ids or English synonym strings.

Demo

LightningDiT-XL-1-256 demo

Class-conditional sample (ImageNet class 207, golden retriever), LightningDiT-XL/1 at 256×256, 250 steps, CFG 6.7, cfg_interval_start=0.125, timestep_shift=0.3, seed 0.

Model Paths

Model	Resolution	Local path
LightningDiT-XL/1	256×256	`./LightningDit-XL-1-256`

Inference

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "./LightningDit-XL-1-256",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
).to("cuda")

class_id = pipe.get_label_ids("golden retriever")[0]
image = pipe(
    class_labels=class_id,
    num_inference_steps=250,
    guidance_scale=6.7,
    cfg_interval_start=0.125,
    timestep_shift=0.3,
    generator=torch.Generator(device="cuda").manual_seed(0),
).images[0]

Citation

@inproceedings{yao2025reconstruction,
  title={Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models},
  author={Yao, Jingfeng and Yang, Bin and Wang, Xinggang},
  booktitle={CVPR},
  year={2025}
}

Sources

1 source

Hugging FacePrimaryVersion fdc4fb0d13e20f4ef2148b40e8dae55a4f426779

huggingface.co/BiliSakura/LightningDiT-diffusers/tree/fdc4fb0d13e20f4ef2148b40e8dae55a4f426779

Verified Oct 9

Model artifacts

1 artifact

LightningDit-XL-1-256/vae/diffusion_pytorch_model.safetensors

safetensors · 266 MB · SHA-256 c8b32dcc4e66…619d · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 1huggingface.co/BiliSakura/LightningDiT-diffusers

--- library_name: diffusers pipeline_tag: unconditional-image-generation tags: - diffusers - lightningdit - image-generation - class-conditional - imagenet - flow-matching license: mit inference: true widget: - output: url: LightningDit-XL-1-256/demo.png language: - en --- # LightningDiT-diffusers Diffusers-ready checkpoints for **LightningDiT** (VA-VAE–aligned latent diffusion with flow matching), converted from [`hustvl/lightningdit-xl-imagenet256-800ep`](https://huggingface.co/hustvl/lightningdit-xl-imagenet256-800ep) for local/offline use. This root folder is a model collection that contains: - `LightningDit-XL-1-256` Each subfolder is a self-contained Diffusers model repo with: - `pipeline.py` (`LightningDiTPipeline`) - `transformer/transformer_lightningdit.py` and weights - `scheduler/scheduler_config.json` (`FlowMatchHeunDiscreteScheduler`, `shift=0.3`) - `vae/` ([`REPA-E/vavae-hf`](https://huggingface.co/REPA-E/vavae-hf)) Each variant embeds English `id2label` in `model_index.json`, so class labels can be passed as ImageNet ids or English synonym strings. ## Demo ![LightningDiT-XL-1-256 demo](LightningDit-XL-1-256/demo.png) Class-conditional sample (ImageNet class **207**, golden retriever), `LightningDiT-XL/1` at 256×256, 250 steps, CFG 6.7, `cfg_interval_start=0.125`, `timestep_shift=0.3`, seed 0. ## Model Paths | Model | Resolution | Local path | | --- | ---: | --- | | LightningDiT-XL/1 | 256×256 | `./LightningDit-XL-1-256` | ## Inference ```python import torch from diffusers import DiffusionPipeline pipe = DiffusionPipeline.from_pretrained( "./LightningDit-XL-1-256", trust_remote_code=True, torch_dtype=torch.bfloat16, ).to("cuda") class_id = pipe.get_label_ids("golden retriever")[0] image = pipe( class_labels=class_id, num_inference_steps=250, guidance_scale=6.7, cfg_interval_start=0.125, timestep_shift=0.3, generator=torch.Generator(device="cuda").manual_seed(0), ).images[0] ``` ## Citation ```bibtex @inproceedings{yao2025reconstruction, title={Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models}, author={Yao, Jingfeng and Yang, Bin and Wang, Xinggang}, booktitle={CVPR}, year={2025} } ```

NoteAug 1huggingface.co/BiliSakura/LightningDiT-diffusers

Source context: 0 downloads · 0 likes · Pipeline unconditional-image-generation · Library diffusers · Repo BiliSakura/LightningDiT-diffusers