---
title: Cosmos-Predict2-14B-Text2Image-gguf
canonical_url: "https://www.modelscope.cn/models/city96/Cosmos-Predict2-14B-Text2Image-gguf"
md_url: "https://www.modelscope.cn/models/city96/Cosmos-Predict2-14B-Text2Image-gguf.md"
repository: city96/Cosmos-Predict2-14B-Text2Image-gguf
last_updated: 2025-06-15
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 777
stars: 0
tags:
  - gguf
---

# Cosmos-Predict2-14B-Text2Image-gguf

> Cosmos-Predict2-14B-Text2Image-gguf - city96 在 ModelScope 开源的模型。This is a direct GGUF conversion of nvidia/Cosmos-Predict2-14B-Text2Image.

- **Repository**: city96/Cosmos-Predict2-14B-Text2Image-gguf
- **Tags**: gguf
- **Downloads**: 777
- **Stars**: 0
- **Last updated**: 2025-06-15

Source: https://www.modelscope.cn/models/city96/Cosmos-Predict2-14B-Text2Image-gguf

---

This is a direct GGUF conversion of [nvidia/Cosmos-Predict2-14B-Text2Image](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Text2Image).

The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:

| Type         | Name                           | Location                          | Download         |
| ------------ | ------------------------------ | --------------------------------- | ---------------- |
| Main Model   | Cosmos-Predict2-14B-Text2Image | `ComfyUI/models/diffusion_models` | GGUF (this repo) |
| Text Encoder | (old) T5-XXL-Encoder           | `ComfyUI/models/text_encoders`    | [Safetensors](https://huggingface.co/comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI/tree/main/text_encoders) |
| VAE          | Wan 2.1 VAE                    | `ComfyUI/models/vae`              | [Safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors) |

[**Example workflow**](media/cosmos-predict2-14b-text2image_workflow.json) - based on the [official example workflow](https://github.com/comfyanonymous/ComfyUI/pull/8517)

[**Example outputs**](media/cosmos-predict2-14b-text2image.png) - sample size of 1, not strictly representative

![sample](media/cosmos-predict2-14b-text2image.png)

### Notes

*As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*