Update README.md
Browse files
README.md
CHANGED
|
@@ -37,6 +37,8 @@ library_name: diffusers
|
|
| 37 |
|
| 38 |
SVDQuant is a post-training quantization technique for 4-bit weights and activations that well maintains visual fidelity. On 12B FLUX.1-dev, it achieves 3.6× memory reduction compared to the BF16 model. By eliminating CPU offloading, it offers 8.7× speedup over the 16-bit model when on a 16GB laptop 4090 GPU, 3× faster than the NF4 W4A16 baseline. On PixArt-∑, it demonstrates significantly superior visual quality over other W4A4 or even W4A8 baselines. "E2E" means the end-to-end latency including the text encoder and VAE decoder.
|
| 39 |
|
|
|
|
|
|
|
| 40 |
## Method
|
| 41 |
#### Quantization Method -- SVDQuant
|
| 42 |
|
|
|
|
| 37 |
|
| 38 |
SVDQuant is a post-training quantization technique for 4-bit weights and activations that well maintains visual fidelity. On 12B FLUX.1-dev, it achieves 3.6× memory reduction compared to the BF16 model. By eliminating CPU offloading, it offers 8.7× speedup over the 16-bit model when on a 16GB laptop 4090 GPU, 3× faster than the NF4 W4A16 baseline. On PixArt-∑, it demonstrates significantly superior visual quality over other W4A4 or even W4A8 baselines. "E2E" means the end-to-end latency including the text encoder and VAE decoder.
|
| 39 |
|
| 40 |
+
`svdq-int4-flux.1-schnell` is an INT4-quantized version of [`FLUX.1-schnell`](https://huggingface.co/black-forest-labs/FLUX.1-schnell), which can generate an image based on a text description.
|
| 41 |
+
|
| 42 |
## Method
|
| 43 |
#### Quantization Method -- SVDQuant
|
| 44 |
|