Instructions to use Fansy/poison with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fansy/poison with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Fansy/poison", 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
add train info
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ inference: true
|
|
| 14 |
|
| 15 |
Welcome to poison model. This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Unlike other anime style models, it has a little realistic style(but not too much), especially in the character painting.
|
| 16 |
|
| 17 |
-
It's
|
| 18 |
|
| 19 |
Compare result:
|
| 20 |
|
|
|
|
| 14 |
|
| 15 |
Welcome to poison model. This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Unlike other anime style models, it has a little realistic style(but not too much), especially in the character painting.
|
| 16 |
|
| 17 |
+
It's finetuned from [anything model](https://huggingface.co/Linaqruf/anything-v3.0),and merge back to anything after training.
|
| 18 |
|
| 19 |
Compare result:
|
| 20 |
|