Instructions to use calcuis/gguf-node with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use calcuis/gguf-node with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("calcuis/gguf-node", dtype=torch.bfloat16, device_map="cuda") prompt = "anime style anime girl with massive fennec ears and one big fluffy tail, she has blonde long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress, walking slowly to the front with sweetie smile, holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,7 +81,7 @@ locate **gguf** from Add Node > extension dropdown menu (between 3d and api; sec
|
|
| 81 |
- gguf vae is able to save memory consumption of your machine
|
| 82 |
- convert your safetensors vae to gguf vae using **convertor (zero)**
|
| 83 |
- then use it with the new **gguf vae loader**
|
| 84 |
-
- gguf vae loader is compatible with both safetensors and gguf file(s)
|
| 85 |
|
| 86 |
### **disclaimer**
|
| 87 |
- some models (original files) as well as part of the codes are obtained from somewhere or provided by someone else and we might not easily spot out the creator/contributor(s) behind, unless it was specified in the source; rather let it blank instead of anonymous/unnamed/unknown
|
|
|
|
| 81 |
- gguf vae is able to save memory consumption of your machine
|
| 82 |
- convert your safetensors vae to gguf vae using **convertor (zero)**
|
| 83 |
- then use it with the new **gguf vae loader**
|
| 84 |
+
- same as gguf clip loaders, gguf vae loader is compatible with both safetensors and gguf file(s)
|
| 85 |
|
| 86 |
### **disclaimer**
|
| 87 |
- some models (original files) as well as part of the codes are obtained from somewhere or provided by someone else and we might not easily spot out the creator/contributor(s) behind, unless it was specified in the source; rather let it blank instead of anonymous/unnamed/unknown
|