Update readme
Browse files
README.md
CHANGED
|
@@ -62,6 +62,7 @@ pipe("A girl smiling", num_inference_steps=4, guidance_scale=0).images[0].save("
|
|
| 62 |
|
| 63 |
### 2-Step, 4-Step, 8-Step LoRA
|
| 64 |
|
|
|
|
| 65 |
```python
|
| 66 |
import torch
|
| 67 |
from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
|
|
@@ -125,6 +126,8 @@ Please use Euler sampler with sgm_uniform scheduler.
|
|
| 125 |
|
| 126 |
### 2-Step, 4-Step, 8-Step LoRA
|
| 127 |
|
|
|
|
|
|
|
| 128 |
1. Prepare your own base model.
|
| 129 |
1. Download the LoRA checkpoint (`sdxl_lightning_Nstep_lora.safetensors`) to `/ComfyUI/models/loras`
|
| 130 |
1. Download our [ComfyUI LoRA workflow](comfyui/sdxl_lightning_workflow_lora.json).
|
|
|
|
| 62 |
|
| 63 |
### 2-Step, 4-Step, 8-Step LoRA
|
| 64 |
|
| 65 |
+
Use LoRA only if you are using non-SDXL base models. Otherwise use our UNet checkpoint for better quality.
|
| 66 |
```python
|
| 67 |
import torch
|
| 68 |
from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
|
|
|
|
| 126 |
|
| 127 |
### 2-Step, 4-Step, 8-Step LoRA
|
| 128 |
|
| 129 |
+
Use LoRA only if you are using non-SDXL base models. Otherwise use our full checkpoint for better quality.
|
| 130 |
+
|
| 131 |
1. Prepare your own base model.
|
| 132 |
1. Download the LoRA checkpoint (`sdxl_lightning_Nstep_lora.safetensors`) to `/ComfyUI/models/loras`
|
| 133 |
1. Download our [ComfyUI LoRA workflow](comfyui/sdxl_lightning_workflow_lora.json).
|