Instructions to use Andyrasika/lora_diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Andyrasika/lora_diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Andyrasika/lora_diffusion", 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
Commit ·
50f0536
1
Parent(s): d3d1b30
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,12 +3,17 @@ license: creativeml-openrail-m
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
```
|
| 8 |
pipeline = DiffusionPipeline.from_pretrained(
|
| 9 |
"Andyrasika/lora_diffusion"
|
| 10 |
,custom_pipeline = "lpw_stable_diffusion"
|
| 11 |
-
,torch_dtype
|
| 12 |
)
|
| 13 |
lora = ("/content/lora_model.safetensors",0.8)
|
| 14 |
pipeline = __load_lora(pipeline=pipeline,lora_path=lora[0],lora_weight=lora[1])
|
|
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
---
|
| 6 |
+
The model is created using the following steps:
|
| 7 |
+
- Find the desired model (checkpoit or lora) on Civitai
|
| 8 |
+
- You can see some conversion scripts in diffusesrs. This time, only the scripts for converting checkpoit and lora are used.
|
| 9 |
+
It depends on the model type of Civitai. If it is a lora model, you need to specify a basic model
|
| 10 |
+
|
| 11 |
|
| 12 |
```
|
| 13 |
pipeline = DiffusionPipeline.from_pretrained(
|
| 14 |
"Andyrasika/lora_diffusion"
|
| 15 |
,custom_pipeline = "lpw_stable_diffusion"
|
| 16 |
+
,torch_dtype=torch.float16
|
| 17 |
)
|
| 18 |
lora = ("/content/lora_model.safetensors",0.8)
|
| 19 |
pipeline = __load_lora(pipeline=pipeline,lora_path=lora[0],lora_weight=lora[1])
|