patrickvonplaten commited on
Commit
6b10b56
0 Parent(s):

Duplicate from ai-forever/kandinsky-2-1

Browse files
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - kandinsky
5
+ duplicated_from: ai-forever/kandinsky-2-1
6
+ ---
model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "KandinskyPipeline",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "text_encoder": [
5
+ "kandinsky",
6
+ "MultilingualCLIP"
7
+ ],
8
+ "tokenizer": [
9
+ "transformers",
10
+ "XLMRobertaTokenizerFast"
11
+ ],
12
+ "scheduler": [
13
+ "diffusers",
14
+ "UnCLIPScheduler"
15
+ ],
16
+ "unet": [
17
+ "diffusers",
18
+ "UNet2DConditionModel"
19
+ ],
20
+ "movq": [
21
+ "diffusers",
22
+ "VQModel"
23
+ ]
24
+ }
movq/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "VQModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 256,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "AttnDownEncoderBlock2D"
16
+ ],
17
+ "in_channels": 3,
18
+ "latent_channels": 4,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "norm_type": "spatial",
22
+ "num_vq_embeddings": 16384,
23
+ "out_channels": 3,
24
+ "sample_size": 32,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "AttnUpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ],
32
+ "vq_embed_dim": 4
33
+ }
movq/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772e09739d742ddee6807add2d3c2fd2a32db53896b5d07a92c729d8c879ce59
3
+ size 271492131
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPScheduler",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "clip_sample": true,
5
+ "clip_sample_range": 2.0,
6
+ "sample_min_value": 1.0,
7
+ "sample_max_value": null,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "variance_type": "learned_range",
11
+ "thresholding": true,
12
+ "beta_schedule": "linear",
13
+ "beta_start": 0.00085,
14
+ "beta_end":0.012
15
+
16
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MultilingualCLIP"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "xlm-roberta",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "output_past": true,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.17.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 250002,
25
+ "numDims": 768,
26
+ "transformerDimensions": 1024
27
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152bab8bc5813ec882ec634c7301978a0ef29340d4c17b3ae77b6468e017dfbe
3
+ size 2242843757
tokenizer/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
unet/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": "text_image",
6
+ "addition_embed_type_num_heads": 64,
7
+ "attention_head_dim": 64,
8
+ "block_out_channels": [
9
+ 384,
10
+ 768,
11
+ 1152,
12
+ 1536
13
+ ],
14
+ "center_input_sample": false,
15
+ "class_embed_type": null,
16
+ "class_embeddings_concat": false,
17
+ "conv_in_kernel": 3,
18
+ "conv_out_kernel": 3,
19
+ "cross_attention_dim": 768,
20
+ "cross_attention_norm": null,
21
+ "down_block_types": [
22
+ "ResnetDownsampleBlock2D",
23
+ "SimpleCrossAttnDownBlock2D",
24
+ "SimpleCrossAttnDownBlock2D",
25
+ "SimpleCrossAttnDownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "dual_cross_attention": false,
29
+ "encoder_hid_dim": 1024,
30
+ "encoder_hid_dim_type": "text_image_proj",
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 3,
35
+ "mid_block_only_cross_attention": null,
36
+ "mid_block_scale_factor": 1,
37
+ "mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
38
+ "norm_eps": 1e-05,
39
+ "norm_num_groups": 32,
40
+ "num_class_embeds": null,
41
+ "only_cross_attention": false,
42
+ "out_channels": 8,
43
+ "projection_class_embeddings_input_dim": null,
44
+ "resnet_out_scale_factor": 1.0,
45
+ "resnet_skip_time_act": false,
46
+ "resnet_time_scale_shift": "scale_shift",
47
+ "sample_size": 64,
48
+ "time_cond_proj_dim": null,
49
+ "time_embedding_act_fn": null,
50
+ "time_embedding_dim": null,
51
+ "time_embedding_type": "positional",
52
+ "timestep_post_act": null,
53
+ "up_block_types": [
54
+ "SimpleCrossAttnUpBlock2D",
55
+ "SimpleCrossAttnUpBlock2D",
56
+ "SimpleCrossAttnUpBlock2D",
57
+ "ResnetUpsampleBlock2D"
58
+ ],
59
+ "upcast_attention": false,
60
+ "use_linear_projection": false
61
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4c63c68860933264eaa290f7f9e308ce5d69a8a3012c26822de98aa056ab30
3
+ size 4914888985