Instructions to use Rin247/Z-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/Z-Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Rin247/Z-Image", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload text_encoder/z_image_fp4-quantization.json with huggingface_hub
Browse files
text_encoder/z_image_fp4-quantization.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format": "FP4",
|
| 3 |
+
"scale": "per-group-16",
|
| 4 |
+
"per_tensor_relative_error": 0.117567,
|
| 5 |
+
"per_tensor_weights_lost": 0.075634,
|
| 6 |
+
"matrices_measured": 253
|
| 7 |
+
}
|