Add model card for MVSplit-DiT

Hi! I'm Niels from the Hugging Face community team. I've updated the model card to include:
- Relevant metadata (`pipeline_tag: text-to-image`).
- Links to the paper, GitHub repository, and project page.
- A brief description of the architecture and the "Mean Mode Screaming" problem it solves.
- Sample usage instructions for image generation as found in your documentation.
- The BibTeX citation.

This will help users discover and use your 1000-layer DiT more effectively!

README.md

@@ -1,3 +1,54 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-to-image
+---
+
+# MVSplit-DiT (1000 layers)
+
+This repository contains the weights for the 1000-layer Diffusion Transformer (DiT) presented in the paper [Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers](https://huggingface.co/papers/2605.06169).
+
+[Project Page](https://erwold.github.io/mv-split/) | [GitHub Repository](https://github.com/erwold/mv-split)
+
+## Introduction
+
+Scaling Diffusion Transformers to extreme depths (hundreds or thousands of layers) introduces a structural vulnerability known as **Mean Mode Screaming (MMS)**. In this state, token representations homogenize, and centered variation is suppressed, leading to model collapse. 
+
+MVSplit-DiT addresses this by using **Mean-Variance Split (MV-Split) Residuals**, which combine a separately gained centered residual update with a leaky trunk-mean replacement. This architecture enables the stable training of DiTs at boundary scales, such as the 1000-layer model provided here.
+
+## Usage
+
+To use this model for image generation, please refer to the official [GitHub repository](https://github.com/erwold/mv-split) for installation instructions and requirements.
+
+### Sampling
+
+You can generate images using the `sample.py` script. The model requires the DiT checkpoint from this repo, a FLUX.2 VAE, and a Qwen3 text encoder.
+
+```bash
+# Custom prompt example
+python sample.py \
+    --checkpoint_path /path/to/model.pt \
+    --flux_vae_path   /path/to/flux2_ae.safetensors \
+    --qwen_model_path Qwen/Qwen3-0.6B \
+    --prompt "a red panda climbing a bamboo stalk" \
+    --output_dir ./samples
+```
+
+### Key sampling flags
+
+| Flag | Default | Meaning |
+|---|---|---|
+| `--image_size` | 256 | Square output side in pixels. |
+| `--num_inference_steps` | 35 | Euler steps for the flow-matching ODE. |
+| `--cfg_scale` | 2.0 | Classifier-free guidance. |
+| `--time_shift_alpha` | 4.0 | Time-shift in the flow schedule (must match training). |
+
+## Citation
+
+```bibtex
+@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},
+}
+```