Upload folder using huggingface_hub
Browse files- inv_latents/ddim_latent-40.pt +3 -0
- model_index.json +24 -0
- unet/config.json +44 -0
- unet/diffusion_pytorch_model.bin +3 -0
inv_latents/ddim_latent-40.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74755c9f84ffb56ec5f7d74aa1b2a0da89927d2b6453be358a54e477ef04419b
|
| 3 |
+
size 394431
|
model_index.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "TuneAVideoPipeline",
|
| 3 |
+
"_diffusers_version": "0.11.1",
|
| 4 |
+
"scheduler": [
|
| 5 |
+
"diffusers",
|
| 6 |
+
"PNDMScheduler"
|
| 7 |
+
],
|
| 8 |
+
"text_encoder": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"CLIPTextModel"
|
| 11 |
+
],
|
| 12 |
+
"tokenizer": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"CLIPTokenizer"
|
| 15 |
+
],
|
| 16 |
+
"unet": [
|
| 17 |
+
"models",
|
| 18 |
+
"UNet3DConditionModel"
|
| 19 |
+
],
|
| 20 |
+
"vae": [
|
| 21 |
+
"diffusers",
|
| 22 |
+
"AutoencoderKL"
|
| 23 |
+
]
|
| 24 |
+
}
|
unet/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet3DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.11.1",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"attention_head_dim": 8,
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
320,
|
| 8 |
+
640,
|
| 9 |
+
1280,
|
| 10 |
+
1280
|
| 11 |
+
],
|
| 12 |
+
"center_input_sample": false,
|
| 13 |
+
"class_embed_type": null,
|
| 14 |
+
"cross_attention_dim": 768,
|
| 15 |
+
"down_block_types": [
|
| 16 |
+
"CrossAttnDownBlock3D",
|
| 17 |
+
"CrossAttnDownBlock3D",
|
| 18 |
+
"CrossAttnDownBlock3D",
|
| 19 |
+
"DownBlock3D"
|
| 20 |
+
],
|
| 21 |
+
"downsample_padding": 1,
|
| 22 |
+
"dual_cross_attention": false,
|
| 23 |
+
"flip_sin_to_cos": true,
|
| 24 |
+
"freq_shift": 0,
|
| 25 |
+
"in_channels": 4,
|
| 26 |
+
"layers_per_block": 2,
|
| 27 |
+
"mid_block_scale_factor": 1,
|
| 28 |
+
"mid_block_type": "UNetMidBlock3DCrossAttn",
|
| 29 |
+
"norm_eps": 1e-05,
|
| 30 |
+
"norm_num_groups": 32,
|
| 31 |
+
"num_class_embeds": null,
|
| 32 |
+
"only_cross_attention": false,
|
| 33 |
+
"out_channels": 4,
|
| 34 |
+
"resnet_time_scale_shift": "default",
|
| 35 |
+
"sample_size": 64,
|
| 36 |
+
"up_block_types": [
|
| 37 |
+
"UpBlock3D",
|
| 38 |
+
"CrossAttnUpBlock3D",
|
| 39 |
+
"CrossAttnUpBlock3D",
|
| 40 |
+
"CrossAttnUpBlock3D"
|
| 41 |
+
],
|
| 42 |
+
"upcast_attention": false,
|
| 43 |
+
"use_linear_projection": false
|
| 44 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a115afac9a3bbe41951ce6f8a0f5149fc9dee3cfab0432da1f933d3bb107e99b
|
| 3 |
+
size 3636825494
|