# Workflow Ep51 Cosmos Predict 2 2b V2w 480p 16fps

> Workflow wrapper imported from `EP51 Cosmos Predict 2 2B v2w 480p 16fps.json`.

- Skill: `steliosot/workflow-ep51-cosmos-predict-2-2b-v2w-480p-16fps` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add steliosot/workflow-ep51-cosmos-predict-2-2b-v2w-480p-16fps`
- Raw SKILL.md: https://api.skillmd.com/api/skills/steliosot/workflow-ep51-cosmos-predict-2-2b-v2w-480p-16fps/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: steliosot (https://skillmd.com/u/steliosot)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/steliosot/workflow-ep51-cosmos-predict-2-2b-v2w-480p-16fps

---


# workflow_ep51_cosmos_predict_2_2b_v2w_480p_16fps

Imported workflow skill generated from `EP51 Cosmos Predict 2 2B v2w 480p 16fps.json`.

## Family

- `txt2img`

## Inputs

- Optional runtime overrides supported by `run(...)`:
  - `prompt`
  - `negative_prompt`
  - `width`, `height`
  - `seed`, `steps`, `cfg`
  - `sampler_name`, `scheduler`, `denoise`
  - `server`, `headers`, `api_prefix`

## Outputs

- Returns JSON with:
  - `status`
  - `prompt_id`
  - `output_images`

## Model Requirements

- `diffusion_model`: `cosmos_predict2_2B_video2world_480p_16fps.safetensors` -> `models/diffusion_models`
- `clip`: `oldt5_xxl_fp8_e4m3fn_scaled.safetensors` -> `models/clip`
- `vae`: `wan_2.1_vae.safetensors` -> `models/vae`

## Custom Node Requirements

- None detected.

## Links

- https://discord.com/invite/gggpkVgBf3
- https://huggingface.co/Comfy-Org/Cosmos_Predict2_repackaged/resolve/main/cosmos_predict2_2B_video2world_480p_16fps.safetensors?download=true
- https://huggingface.co/Comfy-Org/Cosmos_Predict2_repackaged/tree/main
- https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors
- https://huggingface.co/comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI/resolve/main/text_encoders/oldt5_xxl_fp8_e4m3fn_scaled.safetensors
- https://www.youtube.com/@pixaroma

<!-- AUTO-METADATA-START -->
## Routing Metadata

- Family: `txt2img`
- Input modalities: `image, text_prompt`
- Output modalities: `video/mp4`
- Model families: `wan`
- Node count: `13`
- Complexity score: `2`
- Resource profile: `low`
- Estimated runtime: `fast (usually under 30s on modern GPU)`
- Max latent resolution hint: `None`x`None`
- Max sampler steps hint: `35`

## Detected Models

- `diffusion_model`: `cosmos_predict2_2B_video2world_480p_16fps.safetensors` -> `models/diffusion_models`
- `clip`: `oldt5_xxl_fp8_e4m3fn_scaled.safetensors` -> `models/clip`
- `vae`: `wan_2.1_vae.safetensors` -> `models/vae`

## Detected Custom Nodes

- None detected.

## Runtime Warnings

- Large model(s) detected; ensure enough VRAM and disk space.
<!-- AUTO-METADATA-END -->