Instructions to use LyliaEngine/Smooth_Booster_v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/Smooth_Booster_v5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-xl-early-release-v0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LyliaEngine/Smooth_Booster_v5") prompt = "UNICODE\u0000\u00001\u0000g\u0000i\u0000r\u0000l\u0000,\u0000 \u0000(\u0000t\u0000a\u0000n\u0000l\u0000i\u0000n\u0000e\u0000s\u0000)\u0000,\u0000 \u0000b\u0000l\u0000u\u0000e\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000 \u0000w\u0000h\u0000i\u0000t\u0000e\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000s\u0000l\u0000e\u0000n\u0000d\u0000e\u0000r\u0000,\u0000m\u0000e\u0000d\u0000i\u0000u\u0000m\u0000 \u0000a\u0000s\u0000s\u0000,\u0000l\u0000o\u0000n\u0000g\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000h\u0000i\u0000g\u0000h\u0000 \u0000p\u0000o\u0000n\u0000y\u0000t\u0000a\u0000i\u0000l\u0000,\u0000m\u0000e\u0000s\u0000s\u0000y\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000b\u0000a\u0000n\u0000g\u0000s\u0000,\u0000c\u0000r\u0000o\u0000s\u0000s\u0000e\u0000d\u0000 \u0000b\u0000a\u0000n\u0000g\u0000s\u0000,\u0000 \u0000s\u0000u\u0000n\u0000l\u0000i\u0000g\u0000h\u0000t\u0000,\u0000o\u0000u\u0000t\u0000d\u0000o\u0000o\u0000r\u0000s\u0000,\u0000" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,11 +28,11 @@ SMOOTH BOOSTER v.5 Update!
|
|
| 28 |
|
| 29 |
More tweaks based on feedback:
|
| 30 |
|
| 31 |
-
|
| 32 |
|
| 33 |
-
|
| 34 |
|
| 35 |
-
|
| 36 |
|
| 37 |
You can probably risk even weight over 1.0 and get good results - That, of course, depends on the Checkpoints and Models used.
|
| 38 |
|
|
@@ -42,6 +42,14 @@ Less than 2 Loras: Lora weight 0.7 ~ 1.2
|
|
| 42 |
|
| 43 |
More than 2 Loras: Lora weight 0.3 ~ 0.7
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
## Trigger words
|
| 46 |
|
| 47 |
You should use `None` to trigger the image generation.
|
|
|
|
| 28 |
|
| 29 |
More tweaks based on feedback:
|
| 30 |
|
| 31 |
+
Should have a better effect on Illustrious 2 Checkpoints. Still works well on any XL/Illustrious/NoobaAI Checkpoints!
|
| 32 |
|
| 33 |
+
Should do a better job of maintaing the main colors even on higher weights instead of adding light sources of different colors.
|
| 34 |
|
| 35 |
+
Hopefully less blurry, distortions and oversaturation on higher weights for the most part - just don't over do it by going over 1.5 unless it gives the results you want! X_X
|
| 36 |
|
| 37 |
You can probably risk even weight over 1.0 and get good results - That, of course, depends on the Checkpoints and Models used.
|
| 38 |
|
|
|
|
| 42 |
|
| 43 |
More than 2 Loras: Lora weight 0.3 ~ 0.7
|
| 44 |
|
| 45 |
+
## Source
|
| 46 |
+
|
| 47 |
+
https://civitai.red/models/1145743/smooth-detailer-booster-animasdxlpony?modelVersionId=2746768
|
| 48 |
+
|
| 49 |
+
## Credit
|
| 50 |
+
|
| 51 |
+
https://civitai.red/user/DigitalPastel
|
| 52 |
+
|
| 53 |
## Trigger words
|
| 54 |
|
| 55 |
You should use `None` to trigger the image generation.
|