Text-to-Image
Diffusers
Safetensors
English
Pipeline
Non-Autoregressive
Masked-Generative-Transformer
Instructions to use MeissonFlow/Meissonic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MeissonFlow/Meissonic with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MeissonFlow/Meissonic", 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
- Draw Things
- DiffusionBee
JB-Bai commited on
Commit ·
2510f53
1
Parent(s): c0d2579
- .DS_Store +0 -0
- README.md +1 -0
- model_index.json +1 -1
.DS_Store
CHANGED
|
Binary files a/.DS_Store and b/.DS_Store differ
|
|
|
README.md
CHANGED
|
@@ -7,6 +7,7 @@ license: apache-2.0
|
|
| 7 |
[Paper](https://arxiv.org/abs/) | [Code](https://github.com/viiika/Meissonic)
|
| 8 |
|
| 9 |
|
|
|
|
| 10 |
|
| 11 |
## Introduction
|
| 12 |
Meissonic is a non-autoregressive mask image modeling text-to-image synthesis model that can generate high-resolution images. It is designed to run on consumer graphics cards.
|
|
|
|
| 7 |
[Paper](https://arxiv.org/abs/) | [Code](https://github.com/viiika/Meissonic)
|
| 8 |
|
| 9 |
|
| 10 |
+

|
| 11 |
|
| 12 |
## Introduction
|
| 13 |
Meissonic is a non-autoregressive mask image modeling text-to-image synthesis model that can generate high-resolution images. It is designed to run on consumer graphics cards.
|
model_index.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"CLIPTokenizer"
|
| 15 |
],
|
| 16 |
"transformer": [
|
| 17 |
-
"
|
| 18 |
"Transformer2DModel"
|
| 19 |
],
|
| 20 |
"vqvae": [
|
|
|
|
| 14 |
"CLIPTokenizer"
|
| 15 |
],
|
| 16 |
"transformer": [
|
| 17 |
+
"transformer",
|
| 18 |
"Transformer2DModel"
|
| 19 |
],
|
| 20 |
"vqvae": [
|