Text-to-Image
Diffusers
nunchaku-lite
diffuse-compressor
quantized
ernie-image
ernie-image-turbo
svdquant
int4
fp4
Instructions to use rootonchair/ERNIE-Image-Turbo-nunchaku-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rootonchair/ERNIE-Image-Turbo-nunchaku-lite with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rootonchair/ERNIE-Image-Turbo-nunchaku-lite", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,9 +30,7 @@ This repository contains Nunchaku Lite SVDQuant checkpoints for [baidu/ERNIE-Ima
|
|
| 30 |
| `svdq-int4_r32-ernie-image-turbo.safetensors` | INT4 | 32 | Turing, Ampere, Ada |
|
| 31 |
| `svdq-nvfp4_r32-ernie-image-turbo.safetensors` | NVFP4 | 32 | Blackwell |
|
| 32 |
|
| 33 |
-
## Benchmark
|
| 34 |
-
|
| 35 |
-
Detailed benchmark metadata is available in [`benchmarks/summary.json`](benchmarks/summary.json).
|
| 36 |
|
| 37 |

|
| 38 |
|
|
|
|
| 30 |
| `svdq-int4_r32-ernie-image-turbo.safetensors` | INT4 | 32 | Turing, Ampere, Ada |
|
| 31 |
| `svdq-nvfp4_r32-ernie-image-turbo.safetensors` | NVFP4 | 32 | Blackwell |
|
| 32 |
|
| 33 |
+
## Benchmark Results
|
|
|
|
|
|
|
| 34 |
|
| 35 |

|
| 36 |
|