Instructions to use opendiffusionai/sd15vae-texttuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use opendiffusionai/sd15vae-texttuned with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("opendiffusionai/sd15vae-texttuned", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# sd 1.5 vae, text trained demo
|
| 2 |
|
| 3 |
It has been said that the sd vae is not capable of faithful text rendering,
|
|
@@ -38,5 +42,4 @@ If you want to try it out for yourself, you can use the tools in my repo,
|
|
| 38 |
such as
|
| 39 |
|
| 40 |
trainer/cache-utils/create_imgcache_sdvae.py --vae --previewonly \
|
| 41 |
-
--model opendiffusionai/sd15vae-texttrained --data_root someimgdir
|
| 42 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
---
|
| 5 |
# sd 1.5 vae, text trained demo
|
| 6 |
|
| 7 |
It has been said that the sd vae is not capable of faithful text rendering,
|
|
|
|
| 42 |
such as
|
| 43 |
|
| 44 |
trainer/cache-utils/create_imgcache_sdvae.py --vae --previewonly \
|
| 45 |
+
--model opendiffusionai/sd15vae-texttrained --data_root someimgdir
|
|
|