Instructions to use mwnuk/Cosmos3-Edge-severed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mwnuk/Cosmos3-Edge-severed with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mwnuk/Cosmos3-Edge-severed", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Cosmos3-Edge — severed towers (self-contained)
The two streams of the nvidia/Cosmos3-Edge
Mixture-of-Transformers, extracted as independently loadable components, PLUS unmodified copies
of every supporting part needed to recreate the pipeline end-to-end (no dependency on the
original repo). Weights are unmodified slices/copies of the original checkpoint (original tensor
names preserved; see manifest.json in each component). Derivative of NVIDIA Cosmos3-Edge under
the OpenMDW-1.1 license.
Contents
| Folder | Contents | Size |
|---|---|---|
denoiser/ |
Extracted generation stream: add_* attention, *_moe_gen MLPs/norms, latent I/O (proj_in/out), timestep embedder, domain-aware action heads |
2.85 GB |
reasoner/ |
Extracted understanding stream (VLM): embed_tokens, lm_head, und attention/MLPs/norms |
3.89 GB |
vae/ |
Wan VAE (video ↔ 48-ch latents, 4× temporal / 8× spatial) — required at the denoiser boundary | 1.4 GB |
vision_encoder/ |
SigLIP2 + projector — only needed for image/video understanding prompts to the reasoner | 1.0 GB |
text_tokenizer/ |
Tokenizer + chat template — reasoner input | ~20 MB |
scheduler/, root configs |
UniPC scheduler config, model_index.json, transformer/processor configs |
tiny |
assets/ |
The pinned example inputs (i2v image + JSON prompts) used by the verification scripts | ~1 MB |
Both component folders include the 28 per-layer k_norm_und_for_gen interface norms (the
coupling surface between the towers), buffers.safetensors (non-persistent rotary inv_freq,
fp32), and a copy of the original transformer config.
Not included: the original fused transformer/ shards (6.7 GB) — by construction the two
component files reproduce it exactly; fetch nvidia/Cosmos3-Edge if the fused model is needed.
model.safetensors.index.json (the transformers-side index) is kept for reference and refers to
those original shards.
Verification (bit-exactness)
- Cosmos3's MoT attention is one-way: und tokens self-attend causally; gen tokens attend over
concat(und_KV, gen_KV). The und-KV for a fixed prompt is constant across denoising steps (verified bit-identical, 28/28 layers). - Denoiser rebuilt from
denoiser/alone + cached und-KV reproduces the full 4B model's output bit-for-bit (max abs diff 0 on decoded video). - Reasoner rebuilt from
reasoner/alone reproduces the full model's per-layer und-KV bit-for-bit (28/28 layers), from bareinput_ids. - Two build requirements for exactness: run
time_embedderin float32 (_keep_in_fp32_modules), and loadbuffers.safetensors(a bf16-instantiated rotaryinv_freqdiverges).
Usage
Loader/verification scripts and the full architecture analysis live in github.com/wnukmat/cosmos
(a private repository)
(scripts/standalone_severed.py, scripts/reasoner_kv.py, EXTRACTION_PLAN.md).
Requires diffusers >= 0.41.0.dev0 (Cosmos3 classes). Purpose: reference implementation to test
a 3-tower world-action-model rebuild (external VLM + this denoiser + custom action expert)
against known-good components.
License
The weights in this repository are unmodified slices and copies of
nvidia/Cosmos3-Edge, which NVIDIA releases under the
OpenMDW License Agreement, version 1.1. This repository is
distributed under the same agreement; a copy is in LICENSE. Notices of origin from
the original model apply. This is not an NVIDIA release and is not endorsed by NVIDIA.
- Downloads last month
- 24
Model tree for mwnuk/Cosmos3-Edge-severed
Base model
nvidia/Cosmos3-Edge