Downloads · 30 days
0
0% of all-time downloads
BiliSakura/MVSplit-DiT-diffusers
MVSplit-DiT-diffusers is a text-to-image model from BiliSakura. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Diffusers-ready checkpoints for MVSplit-DiT (Mean–Variance Split Residual Diffusion Transformers), converted for local/offline use with a project-owned custom MVSplitDiTPipeline.
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
70
Public
Repo size
29 GB
Likes
0
Public
Click a slice to open those files.
.safetensors28.9 GB · 100%
From the Hugging Face model README
Diffusers-ready checkpoints for MVSplit-DiT (Mean–Variance Split Residual Diffusion Transformers), converted for local/offline use with a project-owned custom MVSplitDiTPipeline.
Re-distribution notice: weights are converted from
StableKirito/mvsplit-dit-1000l. Original work: Mean Mode Screaming. License: Apache 2.0.
| Subfolder | Params | Task | Resolution |
|---|---|---|---|
MVSplit-DiT-1000L/ | 1000L | text-to-image | 256×256 |
Each subfolder is a self-contained Diffusers model repo with pipeline.py, model_index.json, and component weights.

Prompt: a red panda climbing a bamboo stalk — 256×256, 35 steps, CFG 2.0.
cd MVSplit-DiT-1000L
python demo_inference.py
See MVSplit-DiT-1000L/README.md for full usage and recommended settings.
@article{lu2026mms,
title = {Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers},
author = {Lu, Pengqi},
journal = {arXiv preprint arXiv:2605.06169},
year = {2026},
}