Instructions to use lightx2v/Autoencoders with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Autoencoders with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lightx2v/Autoencoders", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use lightx2v/Autoencoders with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -58,22 +58,6 @@ For VAE, the LightX2V team has conducted a series of deep optimizations, derivin
|
|
| 58 |
β Average quality βββ
|
| 59 |
β Potential detail loss
|
| 60 |
|
| 61 |
-
</td>
|
| 62 |
-
<td width="50%">
|
| 63 |
-
|
| 64 |
-
### β‘ **LightTAE Series** (Our Optimization)
|
| 65 |
-
**Features**: Fast Speed + Good Quality π
|
| 66 |
-
|
| 67 |
-
β
Minimal memory usage (~0.4 GB)
|
| 68 |
-
β
Extremely fast inference
|
| 69 |
-
β
**Quality close to official** βββββ
|
| 70 |
-
β
**Significantly surpasses open source TAE**
|
| 71 |
-
|
| 72 |
-
</td>
|
| 73 |
-
</tr>
|
| 74 |
-
</table>
|
| 75 |
-
|
| 76 |
-
|
| 77 |
</td>
|
| 78 |
</tr>
|
| 79 |
<tr>
|
|
@@ -88,6 +72,20 @@ For VAE, the LightX2V team has conducted a series of deep optimizations, derivin
|
|
| 88 |
β
Speed increased by **2-3x**
|
| 89 |
β
Balances quality, speed, and memory π
|
| 90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
---
|
| 93 |
|
|
|
|
| 58 |
β Average quality βββ
|
| 59 |
β Potential detail loss
|
| 60 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
</td>
|
| 62 |
</tr>
|
| 63 |
<tr>
|
|
|
|
| 72 |
β
Speed increased by **2-3x**
|
| 73 |
β
Balances quality, speed, and memory π
|
| 74 |
|
| 75 |
+
</td>
|
| 76 |
+
<td width="50%">
|
| 77 |
+
|
| 78 |
+
### β‘ **LightTAE Series** (Our Optimization)
|
| 79 |
+
**Features**: Fast Speed + Good Quality π
|
| 80 |
+
|
| 81 |
+
β
Minimal memory usage (~0.4 GB)
|
| 82 |
+
β
Extremely fast inference
|
| 83 |
+
β
**Quality close to official** βββββ
|
| 84 |
+
β
**Significantly surpasses open source TAE**
|
| 85 |
+
|
| 86 |
+
</td>
|
| 87 |
+
</tr>
|
| 88 |
+
</table>
|
| 89 |
|
| 90 |
---
|
| 91 |
|