Commit
•
57df7bb
1
Parent(s):
f8b4b32
Upload PixArt-Alpha-DMD 512px diffusers checkpoints
Browse files- model_index.json +24 -0
- scheduler/scheduler_config.json +19 -0
- transformer/config.json +28 -0
- transformer/diffusion_pytorch_model.bin +3 -0
model_index.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "PixArtAlphaPipeline",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 4 |
+
"scheduler": [
|
| 5 |
+
"diffusers",
|
| 6 |
+
"DDPMScheduler"
|
| 7 |
+
],
|
| 8 |
+
"text_encoder": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"T5EncoderModel"
|
| 11 |
+
],
|
| 12 |
+
"tokenizer": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"T5Tokenizer"
|
| 15 |
+
],
|
| 16 |
+
"transformer": [
|
| 17 |
+
"diffusers",
|
| 18 |
+
"Transformer2DModel"
|
| 19 |
+
],
|
| 20 |
+
"vae": [
|
| 21 |
+
"diffusers",
|
| 22 |
+
"AutoencoderKL"
|
| 23 |
+
]
|
| 24 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "DDPMScheduler",
|
| 3 |
+
"_diffusers_version": "0.26.0.dev0",
|
| 4 |
+
"beta_end": 0.02,
|
| 5 |
+
"beta_schedule": "linear",
|
| 6 |
+
"beta_start": 0.0001,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"clip_sample_range": 1.0,
|
| 9 |
+
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
+
"num_train_timesteps": 1000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
+
"rescale_betas_zero_snr": false,
|
| 13 |
+
"sample_max_value": 1.0,
|
| 14 |
+
"steps_offset": 0,
|
| 15 |
+
"thresholding": false,
|
| 16 |
+
"timestep_spacing": "leading",
|
| 17 |
+
"trained_betas": null,
|
| 18 |
+
"variance_type": "fixed_small"
|
| 19 |
+
}
|
transformer/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Transformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.26.0",
|
| 4 |
+
"_name_or_path": "./pretrained_models/pixart_alpha_512px_284000_diffusers/",
|
| 5 |
+
"activation_fn": "gelu-approximate",
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_head_dim": 72,
|
| 8 |
+
"attention_type": "default",
|
| 9 |
+
"caption_channels": 4096,
|
| 10 |
+
"cross_attention_dim": 1152,
|
| 11 |
+
"double_self_attention": false,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"in_channels": 4,
|
| 14 |
+
"norm_elementwise_affine": false,
|
| 15 |
+
"norm_eps": 1e-06,
|
| 16 |
+
"norm_num_groups": 32,
|
| 17 |
+
"norm_type": "ada_norm_single",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_embeds_ada_norm": 1000,
|
| 20 |
+
"num_layers": 28,
|
| 21 |
+
"num_vector_embeds": null,
|
| 22 |
+
"only_cross_attention": false,
|
| 23 |
+
"out_channels": 8,
|
| 24 |
+
"patch_size": 2,
|
| 25 |
+
"sample_size": 64,
|
| 26 |
+
"upcast_attention": false,
|
| 27 |
+
"use_linear_projection": false
|
| 28 |
+
}
|
transformer/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:265aec9adc55f8f52000003b32c65c53ff55de5c3ab5ca2f553ecd4234c19305
|
| 3 |
+
size 2443681081
|