---
title: cosxl
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/cosxl"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/cosxl.md"
repository: AI-ModelScope/cosxl
last_updated: 2024-04-15
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 6.9B
tensor_type:
  - F16
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 3237
stars: 1
---

# cosxl

> cosxl - AI-ModelScope 在 ModelScope 开源的模型。Cos Stable Diffusion XL 1.0 and Cos Stable Diffusion XL 1.0 Edit

AI-ModelScope/cosxl 是 ModelScope 魔搭社区上的 6.9B 参数text-to-image-synthesis模型，采用 other 许可。

- **Repository**: AI-ModelScope/cosxl
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 6.9B
- **Downloads**: 3237
- **Stars**: 1
- **Last updated**: 2024-04-15

Source: https://www.modelscope.cn/models/AI-ModelScope/cosxl

---

# Cos Stable Diffusion XL 1.0 and Cos Stable Diffusion XL 1.0 Edit

Cos Stable Diffusion XL 1.0 Base is tuned to use a Cosine-Continuous EDM VPred schedule. The most notable feature of this schedule change is its capacity to produce the full color range from pitch black to pure white, alongside more subtle improvements to the model's rate-of-change to images across each step.

Edit Stable Diffusion XL 1.0 Base is tuned to use a Cosine-Continuous EDM VPred schedule, and then upgraded to perform instructed image editing. This model takes a source image as input alongside a prompt, and interprets the prompt as an instruction for how to alter the image.

## Usage

It is recommended to use [Stable Swarm UI](https://github.com/Stability-AI/StableSwarmUI) to inference the CosXL model and the edit model.  

Cos Stable Diffusion XL 1.0 can also be used as a regular checkpoint in [ComfyUI](https://github.com/comfyanonymous/ComfyUI)

For an example on how to use Edit Stable Diffusion XL 1.0 see [ComfyUI Example](https://comfyanonymous.github.io/ComfyUI_examples/edit_models/)

## Uses

### Direct Use

The model is for research purposes only. This model is not intended to be state of the art or for consumer use.