| --- |
| license: mit |
| library_name: diffusers |
| pipeline_tag: unconditional-image-generation |
| tags: |
| - diffusers |
| - jlt |
| - image-generation |
| - class-conditional |
| - flux2 |
| - clean-latent |
| widget: |
| - text: golden retriever |
| output: |
| url: demo.png |
| language: |
| - en |
| --- |
| |
| # JLT-diffusers |
|
|
| Native [diffusers](https://github.com/huggingface/diffusers) checkpoints for **JLT** (Clean-Latent Prediction in Latent Diffusion Transformers). Paper: [arXiv:2605.27102](https://arxiv.org/abs/2605.27102). Code: [akatsuki-neo/JLT](https://github.com/akatsuki-neo/JLT). Each variant folder is self-contained: |
|
|
| - `pipeline.py` — `JLTPipeline` |
| - `scheduler/scheduling_jlt.py` — `JLTScheduler` (JLT time `t: 0 → 1`, Heun / Euler) |
| - `transformer/transformer_jlt.py` — `JLTTransformer2DModel` |
| - `vae/` — bundled `AutoencoderKLFlux2` |
|
|
| Load with PyPI `diffusers` and `trust_remote_code=True`. No extra JLT package is required. |
|
|
| ## Demo |
|
|
|  |
|
|
| Class: *golden retriever* (ImageNet 207) — JLT-B/1 at 256×256, 50 Heun steps, `guidance_scale=2.9`, `noise_scale=1.0`, `torch_dtype=bfloat16`, seed 42. These checkpoints are trained and sampled at 256×256 only. |
|
|
| ## Available checkpoints |
|
|
| | Checkpoint | Path | Resolution | Latent | Recommended CFG | |
| | --- | --- | --- | --- | ---: | |
| | JLT-B/1 | [`JLT-B-1/`](JLT-B-1/) | 256×256 | FLUX.2, patch /1 | 2.9 | |
| | JLT-L/1 | [`JLT-L-1/`](JLT-L-1/) | 256×256 | FLUX.2, patch /1 | 2.9 | |
| | JLT-H/1 | [`JLT-H-1/`](JLT-H-1/) | 256×256 | FLUX.2, patch /1 | 2.9 | |
|
|
| ## ImageNet class labels |
|
|
| Each variant keeps an English `id2label` map in `model_index.json`. |
|
|
| - `pipe.id2label` — id → English label |
| - `pipe.labels` — synonym → id |
| - `pipe.get_label_ids("golden retriever")` |
| - `pipe(class_labels="golden retriever", ...)` — string labels resolve automatically |
|
|
| ## Inference |
|
|
| ```python |
| import torch |
| from diffusers import DiffusionPipeline |
| |
| pipe = DiffusionPipeline.from_pretrained( |
| "BiliSakura/JLT-diffusers", |
| subfolder="JLT-B-1", # or "JLT-L-1" / "JLT-H-1" |
| custom_pipeline="pipeline.py", |
| trust_remote_code=True, |
| torch_dtype=torch.bfloat16, |
| ).to("cuda") |
| |
| print(pipe.id2label[207]) |
| image = pipe( |
| class_labels="golden retriever", |
| num_inference_steps=50, |
| guidance_scale=2.9, |
| generator=torch.Generator(device="cuda").manual_seed(42), |
| ).images[0] |
| image.save("demo.png") |
| ``` |
|
|
| ## Citation |
|
|
| ```bibtex |
| @article{fu2026jlt, |
| title={{JLT}: {C}lean-{L}atent {P}rediction in {L}atent {D}iffusion {T}ransformers}, |
| author={Fu, Funing and Wang, Tenghui and Zhou, Guanyu and Cen, Junyong and Zhu, Qichao}, |
| journal = {arXiv preprint arXiv:2605.27102}, |
| year={2026} |
| } |
| ``` |
|
|
