Add dit/base-v1.0/*
Browse files
dit/base-v1.0/text_conditioner/config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AnimaTextConditioner",
|
| 3 |
+
"_diffusers_version": "0.39.0",
|
| 4 |
+
"min_sequence_length": 512,
|
| 5 |
+
"mlp_ratio": 4.0,
|
| 6 |
+
"model_dim": 1024,
|
| 7 |
+
"num_attention_heads": 16,
|
| 8 |
+
"num_layers": 6,
|
| 9 |
+
"source_dim": 1024,
|
| 10 |
+
"target_dim": 1024,
|
| 11 |
+
"target_vocab_size": 32128,
|
| 12 |
+
"use_layer_norm": false,
|
| 13 |
+
"use_self_attention": true
|
| 14 |
+
}
|
dit/base-v1.0/text_conditioner/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdcf606524892e35b270b96fc8bbd8d77e615ab882675a049f6e7c2ff6b71da3
|
| 3 |
+
size 269339400
|
dit/base-v1.0/transformer/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "CosmosTransformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.39.0",
|
| 4 |
+
"adaln_lora_dim": 256,
|
| 5 |
+
"attention_head_dim": 128,
|
| 6 |
+
"concat_padding_mask": true,
|
| 7 |
+
"controlnet_block_every_n": null,
|
| 8 |
+
"crossattn_proj_in_channels": 1024,
|
| 9 |
+
"encoder_hidden_states_channels": 1024,
|
| 10 |
+
"extra_pos_embed_type": null,
|
| 11 |
+
"img_context_dim_in": null,
|
| 12 |
+
"img_context_dim_out": 2048,
|
| 13 |
+
"img_context_num_tokens": 256,
|
| 14 |
+
"in_channels": 16,
|
| 15 |
+
"max_size": [
|
| 16 |
+
128,
|
| 17 |
+
240,
|
| 18 |
+
240
|
| 19 |
+
],
|
| 20 |
+
"mlp_ratio": 4.0,
|
| 21 |
+
"num_attention_heads": 16,
|
| 22 |
+
"num_layers": 28,
|
| 23 |
+
"out_channels": 16,
|
| 24 |
+
"patch_size": [
|
| 25 |
+
1,
|
| 26 |
+
2,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"rope_scale": [
|
| 30 |
+
1.0,
|
| 31 |
+
4.0,
|
| 32 |
+
4.0
|
| 33 |
+
],
|
| 34 |
+
"text_embed_dim": 1024,
|
| 35 |
+
"use_crossattn_projection": false
|
| 36 |
+
}
|
dit/base-v1.0/transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81dc5915fc3c3b170684534ca11ed6c535ddea5658793a801fac53b8d5281065
|
| 3 |
+
size 3912877104
|