Update README.md
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ More checkpoints of our model will be released soon~
|
|
| 43 |
|
| 44 |
| Resolution | Next-DiT Parameter| Text Encoder | Prediction | Download URL |
|
| 45 |
| ---------- | ----------------------- | ------------ | -----------|-------------- |
|
| 46 |
-
| 1024
|
| 47 |
|
| 48 |
## Installation
|
| 49 |
|
|
@@ -51,23 +51,23 @@ More checkpoints of our model will be released soon~
|
|
| 51 |
|
| 52 |
Note: You may want to adjust the CUDA version [according to your driver version](https://docs.nvidia.com/deploy/cuda-compatibility/#default-to-minor-version).
|
| 53 |
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
|
| 60 |
### 2. Install dependencies
|
| 61 |
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
|
| 66 |
### 3. Install ``flash-attn``
|
| 67 |
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
|
| 72 |
## Inference
|
| 73 |
|
|
@@ -86,7 +86,11 @@ huggingface-cli download --resume-download Alpha-VLLM/Lumina-Next-SFT-diffusers
|
|
| 86 |
from diffusers import LuminaText2ImgPipeline
|
| 87 |
import torch
|
| 88 |
|
| 89 |
-
pipeline = LuminaText2ImgPipeline.from_pretrained("/
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
| 91 |
image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. "
|
| 92 |
"Background shows an industrial revolution cityscape with smoky skies and tall, metal structures"
|
|
|
|
| 43 |
|
| 44 |
| Resolution | Next-DiT Parameter| Text Encoder | Prediction | Download URL |
|
| 45 |
| ---------- | ----------------------- | ------------ | -----------|-------------- |
|
| 46 |
+
| 1024 | 2B | [Gemma-2B](https://huggingface.co/google/gemma-2b) | Rectified Flow | [hugging face](https://huggingface.co/Alpha-VLLM/Lumina-Next-SFT) |
|
| 47 |
|
| 48 |
## Installation
|
| 49 |
|
|
|
|
| 51 |
|
| 52 |
Note: You may want to adjust the CUDA version [according to your driver version](https://docs.nvidia.com/deploy/cuda-compatibility/#default-to-minor-version).
|
| 53 |
|
| 54 |
+
```bash
|
| 55 |
+
conda create -n Lumina_T2X -y
|
| 56 |
+
conda activate Lumina_T2X
|
| 57 |
+
conda install python=3.11 pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia -y
|
| 58 |
+
```
|
| 59 |
|
| 60 |
### 2. Install dependencies
|
| 61 |
|
| 62 |
+
```bash
|
| 63 |
+
pip install diffusers huggingface_hub
|
| 64 |
+
```
|
| 65 |
|
| 66 |
### 3. Install ``flash-attn``
|
| 67 |
|
| 68 |
+
```bash
|
| 69 |
+
pip install flash-attn --no-build-isolation
|
| 70 |
+
```
|
| 71 |
|
| 72 |
## Inference
|
| 73 |
|
|
|
|
| 86 |
from diffusers import LuminaText2ImgPipeline
|
| 87 |
import torch
|
| 88 |
|
| 89 |
+
pipeline = LuminaText2ImgPipeline.from_pretrained("/path/to/ckpt/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16).to("cuda")
|
| 90 |
+
|
| 91 |
+
# or you can download the model using code directly
|
| 92 |
+
# pipeline = LuminaText2ImgPipeline.from_pretrained("Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16).to("cuda")
|
| 93 |
+
|
| 94 |
|
| 95 |
image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. "
|
| 96 |
"Background shows an industrial revolution cityscape with smoky skies and tall, metal structures"
|