Upload folder using huggingface_hub
Browse files- 25yqrnl7/samples_39297024/text_encoder/config.json +24 -0
- 25yqrnl7/samples_39297024/text_encoder/model.safetensors +3 -0
- 25yqrnl7/samples_39297024/text_encoder_2/config.json +24 -0
- 25yqrnl7/samples_39297024/text_encoder_2/model.safetensors +3 -0
- 25yqrnl7/samples_39297024/unet/config.json +73 -0
- 25yqrnl7/samples_39297024/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- 25yqrnl7/samples_39297024/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- 25yqrnl7/samples_39297024/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
25yqrnl7/samples_39297024/text_encoder/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"transformers_version": "4.57.1",
|
| 23 |
+
"vocab_size": 49408
|
| 24 |
+
}
|
25yqrnl7/samples_39297024/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4364a536c289e156f997ca4d97e8ca418056d7e8f578fb417a5cec392e935c41
|
| 3 |
+
size 492265168
|
25yqrnl7/samples_39297024/text_encoder_2/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModelWithProjection"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_size": 1280,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5120,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 20,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 1280,
|
| 22 |
+
"transformers_version": "4.57.1",
|
| 23 |
+
"vocab_size": 49408
|
| 24 |
+
}
|
25yqrnl7/samples_39297024/text_encoder_2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b720876534f2e50498dcbd1c2464da4c7fcb95499302117f7837e122dfebf899
|
| 3 |
+
size 2778702264
|
25yqrnl7/samples_39297024/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.35.2",
|
| 4 |
+
"_name_or_path": "checkpoints/25yqrnl7/samples_11587584/unet",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": "text_time",
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": 256,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20
|
| 13 |
+
],
|
| 14 |
+
"attention_type": "default",
|
| 15 |
+
"block_out_channels": [
|
| 16 |
+
320,
|
| 17 |
+
640,
|
| 18 |
+
1280
|
| 19 |
+
],
|
| 20 |
+
"center_input_sample": false,
|
| 21 |
+
"class_embed_type": null,
|
| 22 |
+
"class_embeddings_concat": false,
|
| 23 |
+
"conv_in_kernel": 3,
|
| 24 |
+
"conv_out_kernel": 3,
|
| 25 |
+
"cross_attention_dim": 2048,
|
| 26 |
+
"cross_attention_norm": null,
|
| 27 |
+
"down_block_types": [
|
| 28 |
+
"DownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"CrossAttnDownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"dropout": 0.0,
|
| 34 |
+
"dual_cross_attention": false,
|
| 35 |
+
"encoder_hid_dim": null,
|
| 36 |
+
"encoder_hid_dim_type": null,
|
| 37 |
+
"flip_sin_to_cos": true,
|
| 38 |
+
"freq_shift": 0,
|
| 39 |
+
"in_channels": 4,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 44 |
+
"norm_eps": 1e-05,
|
| 45 |
+
"norm_num_groups": 32,
|
| 46 |
+
"num_attention_heads": null,
|
| 47 |
+
"num_class_embeds": null,
|
| 48 |
+
"only_cross_attention": false,
|
| 49 |
+
"out_channels": 4,
|
| 50 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 51 |
+
"resnet_out_scale_factor": 1.0,
|
| 52 |
+
"resnet_skip_time_act": false,
|
| 53 |
+
"resnet_time_scale_shift": "default",
|
| 54 |
+
"reverse_transformer_layers_per_block": null,
|
| 55 |
+
"sample_size": 128,
|
| 56 |
+
"time_cond_proj_dim": null,
|
| 57 |
+
"time_embedding_act_fn": null,
|
| 58 |
+
"time_embedding_dim": null,
|
| 59 |
+
"time_embedding_type": "positional",
|
| 60 |
+
"timestep_post_act": null,
|
| 61 |
+
"transformer_layers_per_block": [
|
| 62 |
+
1,
|
| 63 |
+
2,
|
| 64 |
+
10
|
| 65 |
+
],
|
| 66 |
+
"up_block_types": [
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"UpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": null,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
25yqrnl7/samples_39297024/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44215173eacaa8f5d44ddc1952e5e6bdb11746b11fcb6f2c44767c5067d4f026
|
| 3 |
+
size 9988139160
|
25yqrnl7/samples_39297024/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24c4bea73f3b5f3c8a320bcece74886092d495ba77e86064e4cf1fc60696cd0c
|
| 3 |
+
size 281938304
|
25yqrnl7/samples_39297024/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|