Update README.md
Browse files
README.md
CHANGED
@@ -52,7 +52,7 @@ license: apache-2.0
|
|
52 |
|
53 |
**TurboRender-flux-dev** is a plug-and-play LoRA designed to **not only speeds up generation but also delivers better details!**
|
54 |
|
55 |
-
TurboRender-flux-dev generates better results compared to the original flux dev baseline within the **4-
|
56 |
|
57 |
The LoRA was trained in just 8 hours with 1x A100 GPU.
|
58 |
|
@@ -67,7 +67,7 @@ image = pipe(
|
|
67 |
guidance_scale=3.5,
|
68 |
height=1024,
|
69 |
width=1024,
|
70 |
-
num_inference_steps=
|
71 |
generator=torch.Generator(device='cuda').manual_seed(0)
|
72 |
).images[0]
|
73 |
```
|
|
|
52 |
|
53 |
**TurboRender-flux-dev** is a plug-and-play LoRA designed to **not only speeds up generation but also delivers better details!**
|
54 |
|
55 |
+
TurboRender-flux-dev generates better results compared to the original flux dev baseline within the **4-6 step range**. Additionally, when using more steps (we suggest 10-15 steps), it delivers **even finer details**, offering improved performance compared with LCM LoRA.
|
56 |
|
57 |
The LoRA was trained in just 8 hours with 1x A100 GPU.
|
58 |
|
|
|
67 |
guidance_scale=3.5,
|
68 |
height=1024,
|
69 |
width=1024,
|
70 |
+
num_inference_steps=8,
|
71 |
generator=torch.Generator(device='cuda').manual_seed(0)
|
72 |
).images[0]
|
73 |
```
|