Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- model_index.json +24 -0
- scheduler/scheduler_config.json +16 -0
- text_encoder/config.json +13 -0
- text_encoder/model.fp16.safetensors +3 -0
- tokenizer/special_tokens_map.json +51 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +54 -0
- transformer/config.json +20 -0
- transformer/diffusion_pytorch_model.fp16.safetensors +3 -0
- vae/config.json +38 -0
- vae/diffusion_pytorch_model.fp16.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
model_index.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "SanaPipeline",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"scheduler": [
|
5 |
+
"diffusers",
|
6 |
+
"FlowMatchEulerDiscreteScheduler"
|
7 |
+
],
|
8 |
+
"text_encoder": [
|
9 |
+
"transformers_modules.visheratin.mexma-siglip.c284b0df4f065b1a702913fc0d79db7f254df274.mexma_siglip",
|
10 |
+
"MexmaSigLIP"
|
11 |
+
],
|
12 |
+
"tokenizer": [
|
13 |
+
"transformers",
|
14 |
+
"XLMRobertaTokenizerFast"
|
15 |
+
],
|
16 |
+
"transformer": [
|
17 |
+
"diffusers",
|
18 |
+
"SanaTransformer2DModel"
|
19 |
+
],
|
20 |
+
"vae": [
|
21 |
+
"diffusers",
|
22 |
+
"AutoencoderKL"
|
23 |
+
]
|
24 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"base_image_seq_len": 256,
|
5 |
+
"base_shift": 0.5,
|
6 |
+
"invert_sigmas": false,
|
7 |
+
"max_image_seq_len": 4096,
|
8 |
+
"max_shift": 1.15,
|
9 |
+
"num_train_timesteps": 1000,
|
10 |
+
"shift": 3.0,
|
11 |
+
"shift_terminal": null,
|
12 |
+
"use_beta_sigmas": false,
|
13 |
+
"use_dynamic_shifting": false,
|
14 |
+
"use_exponential_sigmas": false,
|
15 |
+
"use_karras_sigmas": false
|
16 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "visheratin/mexma-siglip",
|
3 |
+
"architectures": [
|
4 |
+
"MexmaSigLIP"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "visheratin/mexma-siglip--mexma_siglip.MexmaSigLIPConfig",
|
8 |
+
"AutoModel": "visheratin/mexma-siglip--mexma_siglip.MexmaSigLIP"
|
9 |
+
},
|
10 |
+
"optimized": false,
|
11 |
+
"torch_dtype": "bfloat16",
|
12 |
+
"transformers_version": "4.46.3"
|
13 |
+
}
|
text_encoder/model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27bc370ee5c95b29ebc1207960299d754f9715648c332709fc6a3b4b8dea9c9a
|
3 |
+
size 1120090484
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
|
3 |
+
size 17082734
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
transformer/config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "SanaTransformer2DModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"attention_bias": false,
|
5 |
+
"attention_head_dim": 32,
|
6 |
+
"caption_channels": 1024,
|
7 |
+
"cross_attention_dim": 2240,
|
8 |
+
"cross_attention_head_dim": 112,
|
9 |
+
"dropout": 0.0,
|
10 |
+
"in_channels": 16,
|
11 |
+
"mlp_ratio": 2.5,
|
12 |
+
"norm_elementwise_affine": false,
|
13 |
+
"norm_eps": 1e-06,
|
14 |
+
"num_attention_heads": 70,
|
15 |
+
"num_cross_attention_heads": 20,
|
16 |
+
"num_layers": 20,
|
17 |
+
"out_channels": 16,
|
18 |
+
"patch_size": 1,
|
19 |
+
"sample_size": 64
|
20 |
+
}
|
transformer/diffusion_pytorch_model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8ffd113e8e5e3f662eb3701d3dc17fbf80690b48b42d60345410f58b97b028
|
3 |
+
size 3203093344
|
vae/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "AuraDiffusion/16ch-vae",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"force_upcast": false,
|
19 |
+
"in_channels": 3,
|
20 |
+
"latent_channels": 16,
|
21 |
+
"latents_mean": null,
|
22 |
+
"latents_std": null,
|
23 |
+
"layers_per_block": 2,
|
24 |
+
"mid_block_add_attention": false,
|
25 |
+
"norm_num_groups": 32,
|
26 |
+
"out_channels": 3,
|
27 |
+
"sample_size": 1024,
|
28 |
+
"scaling_factor": 0.18215,
|
29 |
+
"shift_factor": 0,
|
30 |
+
"up_block_types": [
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D",
|
33 |
+
"UpDecoderBlock2D",
|
34 |
+
"UpDecoderBlock2D"
|
35 |
+
],
|
36 |
+
"use_post_quant_conv": true,
|
37 |
+
"use_quant_conv": true
|
38 |
+
}
|
vae/diffusion_pytorch_model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a27d33cadf456598eee3cf5638ba3e8e01dd020a5f9c80c1a7b162bf97096701
|
3 |
+
size 163460798
|