-
-
Notifications
You must be signed in to change notification settings - Fork 14
How to ONNX
ForserX edited this page May 2, 2023
·
9 revisions
Before starting the generation, it is necessary to convert from the original model to ONNX format.

- Open convert wnd
- Drop your (.ckpt/.safetensors/diffusers) model into form.
- Check that the parameters are correct. 1 - the format of your model. 2. ONNX
- Click to convert.
- Wait while the program reports readiness
| File/Folder | Useful information |
|---|---|
| cnet | unet for ControlNet |
| feature_extractor | |
| safety_checker | nsfw checker |
| scheduler | |
| text_encoder | |
| tokenizer | |
| unet | |
| vae_decoder | Default model VAE |
| vae_encoder | Default model VAE |
| model_index.json | Base model info |
| logo.(png/jpg) | Optional: Preview pick |
All models are forcibly optimized in float16 so that you have enough VRAM to use Textual Inversion/LoRA/LyCORIS/etc...