Instructions to use madebyollin/texture-fix-vae-for-qwen-image-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madebyollin/texture-fix-vae-for-qwen-image-2.1 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/texture-fix-vae-for-qwen-image-2.1", 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
Fix whitespace
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ tags:
|
|
| 14 |
Qwen-Image-2.1-VAE-Texture-Fix is the [Qwen-Image-2.1 VAE](https://huggingface.co/Qwen/Qwen-Image-2.1/tree/main/vae), but finetuned to produce cleaner textures with no checkerboard artifacts.
|
| 15 |
|
| 16 |
Qwen-Image-2.1-VAE-Texture-Fix's improved decoding is most noticeable in detailed, photo-style images.
|
|
|
|
| 17 |
<details>
|
| 18 |
<summary>Comparison Settings</summary>
|
| 19 |
|
|
@@ -29,7 +30,6 @@ The latents for the VAE comparison image below were generated by Qwen-Image-2.1
|
|
| 29 |
|  |  |
|
| 30 |
|  |  |
|
| 31 |
|
| 32 |
-
|
| 33 |
# Usage
|
| 34 |
|
| 35 |
**ComfyUI**
|
|
|
|
| 14 |
Qwen-Image-2.1-VAE-Texture-Fix is the [Qwen-Image-2.1 VAE](https://huggingface.co/Qwen/Qwen-Image-2.1/tree/main/vae), but finetuned to produce cleaner textures with no checkerboard artifacts.
|
| 15 |
|
| 16 |
Qwen-Image-2.1-VAE-Texture-Fix's improved decoding is most noticeable in detailed, photo-style images.
|
| 17 |
+
|
| 18 |
<details>
|
| 19 |
<summary>Comparison Settings</summary>
|
| 20 |
|
|
|
|
| 30 |
|  |  |
|
| 31 |
|  |  |
|
| 32 |
|
|
|
|
| 33 |
# Usage
|
| 34 |
|
| 35 |
**ComfyUI**
|