Instructions to use Silan10/flux-quantized-bitsandbytes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Silan10/flux-quantized-bitsandbytes with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Silan10/flux-quantized-bitsandbytes", 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
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: text-to-image
|
|
| 16 |
|
| 17 |
## Model Overview
|
| 18 |
|
| 19 |
-
`Silan10/
|
| 20 |
[`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 21 |
text-to-image model. In this version, the **`transformer`**, **`text_encoder`** and
|
| 22 |
**`text_encoder_2`** components have been quantized to 8-bit precision using bitsandbytes.
|
|
@@ -32,7 +32,7 @@ import torch
|
|
| 32 |
import os
|
| 33 |
from diffusers import FluxPipeline
|
| 34 |
|
| 35 |
-
model_path = "Silan10/
|
| 36 |
|
| 37 |
print("Loading pipeline...")
|
| 38 |
|
|
|
|
| 16 |
|
| 17 |
## Model Overview
|
| 18 |
|
| 19 |
+
`Silan10/flux-quantized-bitsandbytes` is an **8-bit quantized version** of the
|
| 20 |
[`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 21 |
text-to-image model. In this version, the **`transformer`**, **`text_encoder`** and
|
| 22 |
**`text_encoder_2`** components have been quantized to 8-bit precision using bitsandbytes.
|
|
|
|
| 32 |
import os
|
| 33 |
from diffusers import FluxPipeline
|
| 34 |
|
| 35 |
+
model_path = "Silan10/flux-quantized-bitsandbytes"
|
| 36 |
|
| 37 |
print("Loading pipeline...")
|
| 38 |
|