Instructions to use F16/z-image-turbo-sda with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use F16/z-image-turbo-sda with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("F16/z-image-turbo-sda", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Why does applying this LoRA to certain ZIT models cause the image to break?
#5
by daijava - opened
Applying SDA to Zimage Turbo NSFW by Stable Yogi causes the image to completely break, unless the weight of this lora is reduced to 0.1—though, in practice, this is virtually indistinguishable from not using the LoRA at all.
While I cannot confirm the specific cause, SDA is known to have substantial compatibility issues. Please try an alternative plugin version I developed, which relies solely on code implementation to prevent any interference with model weights