Instructions to use madtune/pixeldit-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madtune/pixeldit-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/PixelDiT-1300M-1024px", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("madtune/pixeldit-diffusers") 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
Delete pixeldit/configuration_pixeldit.py with huggingface_hub
Browse files
pixeldit/configuration_pixeldit.py
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 1 |
-
from transformers import PretrainedConfig
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
class PixelDiTConfig(PretrainedConfig):
|
| 5 |
-
model_type = "pixeldit"
|
| 6 |
-
|
| 7 |
-
def __init__(
|
| 8 |
-
self,
|
| 9 |
-
in_channels=3,
|
| 10 |
-
num_groups=24,
|
| 11 |
-
hidden_size=1536,
|
| 12 |
-
pixel_hidden_size=16,
|
| 13 |
-
pixel_attn_hidden_size=1152,
|
| 14 |
-
pixel_num_groups=16,
|
| 15 |
-
patch_depth=14,
|
| 16 |
-
pixel_depth=2,
|
| 17 |
-
num_text_blocks=4,
|
| 18 |
-
patch_size=16,
|
| 19 |
-
txt_embed_dim=2304,
|
| 20 |
-
txt_max_length=300,
|
| 21 |
-
use_text_rope=True,
|
| 22 |
-
text_rope_theta=10000.0,
|
| 23 |
-
repa_encoder_index=-1,
|
| 24 |
-
use_pixel_abs_pos=True,
|
| 25 |
-
**kwargs,
|
| 26 |
-
):
|
| 27 |
-
super().__init__(**kwargs)
|
| 28 |
-
self.in_channels = in_channels
|
| 29 |
-
self.num_groups = num_groups
|
| 30 |
-
self.hidden_size = hidden_size
|
| 31 |
-
self.pixel_hidden_size = pixel_hidden_size
|
| 32 |
-
self.pixel_attn_hidden_size = pixel_attn_hidden_size
|
| 33 |
-
self.pixel_num_groups = pixel_num_groups
|
| 34 |
-
self.patch_depth = patch_depth
|
| 35 |
-
self.pixel_depth = pixel_depth
|
| 36 |
-
self.num_text_blocks = num_text_blocks
|
| 37 |
-
self.patch_size = patch_size
|
| 38 |
-
self.txt_embed_dim = txt_embed_dim
|
| 39 |
-
self.txt_max_length = txt_max_length
|
| 40 |
-
self.use_text_rope = use_text_rope
|
| 41 |
-
self.text_rope_theta = text_rope_theta
|
| 42 |
-
self.repa_encoder_index = repa_encoder_index
|
| 43 |
-
self.use_pixel_abs_pos = use_pixel_abs_pos
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|