Instructions to use AX1Y2JP/Krea-2-Turbo-INT8-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AX1Y2JP/Krea-2-Turbo-INT8-ConvRot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AX1Y2JP/Krea-2-Turbo-INT8-ConvRot", 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
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- ComparisonA.webp +2 -2
- ComparisonB.webp +2 -2
- ComparisonC.webp +3 -0
- README.md +1 -0
- krea-2-turbo-int8-convrot-aggressive.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
ComparisonA.webp filter=lfs diff=lfs merge=lfs -text
|
| 37 |
ComparisonB.webp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 36 |
ComparisonA.webp filter=lfs diff=lfs merge=lfs -text
|
| 37 |
ComparisonB.webp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
ComparisonC.webp filter=lfs diff=lfs merge=lfs -text
|
ComparisonA.webp
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
ComparisonB.webp
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
ComparisonC.webp
ADDED
|
Git LFS Details
|
README.md
CHANGED
|
@@ -15,4 +15,5 @@ inference: false
|
|
| 15 |
A Krea 2 model quantized to INT8 with ConvRot using a conservative quantization policy.
|
| 16 |
<img src="ComparisonA.webp" width="1000">
|
| 17 |
<img src="ComparisonB.webp" width="1000">
|
|
|
|
| 18 |
Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.
|
|
|
|
| 15 |
A Krea 2 model quantized to INT8 with ConvRot using a conservative quantization policy.
|
| 16 |
<img src="ComparisonA.webp" width="1000">
|
| 17 |
<img src="ComparisonB.webp" width="1000">
|
| 18 |
+
<img src="ComparisonC.webp" width="1000">
|
| 19 |
Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.
|
krea-2-turbo-int8-convrot-aggressive.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965453d86a1def69fa597eb56d56ded15ddb511bb6073590c7704679e6d202b8
|
| 3 |
+
size 13757824159
|