Instructions to use 8BitStudio/Aniimage-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 8BitStudio/Aniimage-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("8BitStudio/Aniimage-2", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -140,8 +140,8 @@ The model generates male characters less reliably than female characters, it may
|
|
| 140 |
|
| 141 |
## What's Next
|
| 142 |
|
| 143 |
-
Aniimage-3 is currently in the works and will have
|
| 144 |
-
The model will also have
|
| 145 |
Aniimage-2 used incorrect Min-SNR loss weighting with its v-prediction objective, causing near-pure-noise timesteps to receive excessive emphasis. This has been corrected for Aniimage-3.
|
| 146 |
Aniimage-3 also uses a much higher-quality dataset with improved filtering. More than 100,000 low-quality images from the Aniimage-2 dataset were removed.
|
| 147 |
|
|
|
|
| 140 |
|
| 141 |
## What's Next
|
| 142 |
|
| 143 |
+
Aniimage-3 is currently in the works and will have a much higher parameter count: 738.1M parameters compared to aniimage-2 and aniimage-1's 441.9M parameters.
|
| 144 |
+
The model will also have 1.5 million unique images, 25% more than the 1.2 million Aniimage-2 has.
|
| 145 |
Aniimage-2 used incorrect Min-SNR loss weighting with its v-prediction objective, causing near-pure-noise timesteps to receive excessive emphasis. This has been corrected for Aniimage-3.
|
| 146 |
Aniimage-3 also uses a much higher-quality dataset with improved filtering. More than 100,000 low-quality images from the Aniimage-2 dataset were removed.
|
| 147 |
|