Instructions to use dataautogpt3/ProteusV0.3-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dataautogpt3/ProteusV0.3-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dataautogpt3/ProteusV0.3-Lightning", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Anime Girl holding a sign that says 'Proteus Lighting'" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ widget:
|
|
| 12 |
license: gpl-3.0
|
| 13 |
---
|
| 14 |
<Gallery />
|
| 15 |
-
## ProteusV0.3-
|
| 16 |
|
| 17 |
using the new lighting method released by bytedance for faster infernce with minial loss interms of quality and prompt comprehension.
|
| 18 |
|
|
@@ -23,9 +23,9 @@ Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its
|
|
| 23 |
In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.
|
| 24 |
|
| 25 |
|
| 26 |
-
## Settings for ProteusV0.3-
|
| 27 |
|
| 28 |
-
Use these settings for the best results with ProteusV0.3-
|
| 29 |
|
| 30 |
CFG Scale: Use a CFG scale of 1 to 2
|
| 31 |
|
|
@@ -59,7 +59,7 @@ vae = AutoencoderKL.from_pretrained(
|
|
| 59 |
|
| 60 |
# Configure the pipeline
|
| 61 |
pipe = StableDiffusionXLPipeline.from_pretrained(
|
| 62 |
-
"dataautogpt3/ProteusV0.3-
|
| 63 |
vae=vae,
|
| 64 |
torch_dtype=torch.float16
|
| 65 |
)
|
|
|
|
| 12 |
license: gpl-3.0
|
| 13 |
---
|
| 14 |
<Gallery />
|
| 15 |
+
## ProteusV0.3-Lightning
|
| 16 |
|
| 17 |
using the new lighting method released by bytedance for faster infernce with minial loss interms of quality and prompt comprehension.
|
| 18 |
|
|
|
|
| 23 |
In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.
|
| 24 |
|
| 25 |
|
| 26 |
+
## Settings for ProteusV0.3-Lightning
|
| 27 |
|
| 28 |
+
Use these settings for the best results with ProteusV0.3-Lightning:
|
| 29 |
|
| 30 |
CFG Scale: Use a CFG scale of 1 to 2
|
| 31 |
|
|
|
|
| 59 |
|
| 60 |
# Configure the pipeline
|
| 61 |
pipe = StableDiffusionXLPipeline.from_pretrained(
|
| 62 |
+
"dataautogpt3/ProteusV0.3-Lightning",
|
| 63 |
vae=vae,
|
| 64 |
torch_dtype=torch.float16
|
| 65 |
)
|