Instructions to use madebyollin/sdxl-vae-fp16-fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madebyollin/sdxl-vae-fp16-fix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("madebyollin/sdxl-vae-fp16-fix", 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
Commit ·
6d10734
1
Parent(s): 1d890c9
Improved decoder weights
Browse filesImproved decoder weights
* Further-reduced risk of NaNs
* Further-reduced discrepancies with original SDXL-VAE (0.9) decoder
Encoder weights are unchanged.
diffusion_pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 334712113
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37eb3e09ae1ce3d6891ddf809ca927b618e501091142cf07fdd9cd170e3a046f
|
| 3 |
size 334712113
|
diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 334643238
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c
|
| 3 |
size 334643238
|
sdxl_vae.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 334641162
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1
|
| 3 |
size 334641162
|