Instructions to use madebyollin/taef1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madebyollin/taef1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("madebyollin/taef1", 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
Possible to work with Comfy?
#1
by BuffMcBigHuge - opened
memory_used = self.memory_used_encode(pixel_samples.shape, self.vae_dtype)
^^^^^^^^^^^^^^
AttributeError: 'VAE' object has no attribute 'vae_dtype'
Ah I found these:
https://github.com/madebyollin/taesd/raw/refs/heads/main/taef1_encoder.pth
https://github.com/madebyollin/taesd/raw/refs/heads/main/taef1_decoder.pth
Placing them in models/vae_approx works.