Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,14 @@ by *Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.*
|
|
| 16 |
It is a distilled consistency adapter for [`segmind/Segmind-Vega`]("https://huggingface.co/segmind/Segmind_Vega") that allows
|
| 17 |
to reduce the number of inference steps to only between **2 - 8 steps**.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
| Model | Params / M |
|
| 20 |
|----------------------------------------------------------------------------|------------|
|
| 21 |
| [lcm-lora-sdv1-5](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5) | 67.5 |
|
|
|
|
| 16 |
It is a distilled consistency adapter for [`segmind/Segmind-Vega`]("https://huggingface.co/segmind/Segmind_Vega") that allows
|
| 17 |
to reduce the number of inference steps to only between **2 - 8 steps**.
|
| 18 |
|
| 19 |
+
# Image comparison (Segmind-VegaRT vs SDXL-Turbo)
|
| 20 |
+
|
| 21 |
+

|
| 22 |
+
|
| 23 |
+

|
| 24 |
+
|
| 25 |
+

|
| 26 |
+
|
| 27 |
| Model | Params / M |
|
| 28 |
|----------------------------------------------------------------------------|------------|
|
| 29 |
| [lcm-lora-sdv1-5](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5) | 67.5 |
|