---
title: taef1
canonical_url: "https://www.modelscope.cn/models/silveroxides/taef1"
md_url: "https://www.modelscope.cn/models/silveroxides/taef1.md"
repository: silveroxides/taef1
last_updated: 2025-05-12
license: mit
parameters: 2.5M
tensor_type:
  - F32
library_name:
  - pytorch
  - safetensors
  - diffusers
frameworks:
  - pytorch
downloads: 368
stars: 0
---

# taef1

> taef1 - silveroxides 在 ModelScope 开源的模型。🍰 Tiny AutoEncoder for FLUX.1

silveroxides/taef1 是 ModelScope 魔搭社区上的 2.5M 参数机器学习模型，采用 mit 许可。

- **Repository**: silveroxides/taef1
- **License**: mit
- **Parameters**: 2.5M
- **Downloads**: 368
- **Stars**: 0
- **Last updated**: 2025-05-12

Source: https://www.modelscope.cn/models/silveroxides/taef1

---

# 🍰 Tiny AutoEncoder for FLUX.1

[TAEF1](https://github.com/madebyollin/taesd) is very tiny autoencoder which uses the same "latent API" as FLUX.1's VAE.
FLUX.1 is useful for real-time previewing of the FLUX.1 generation process.

This repo contains `.safetensors` versions of the TAEF1 weights.

## Using in 🧨 diffusers

```python
import torch
from diffusers import FluxPipeline, AutoencoderTiny

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.bfloat16)
pipe.enable_sequential_cpu_offload()

prompt = "slice of delicious New York-style berry cheesecake"
image = pipe(
    prompt,
    guidance_scale=0.0,
    num_inference_steps=4,
    max_sequence_length=256,
).images[0]
image.save("cheesecake.png")
```


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/630447d40547362a22a969a2/5FbkYmKc4JsULnskQmzLe.jpeg)