Hugging Face's logo

kakaobrain
/
karlo-v1-alpha

Text-to-Image
Diffusers
Safetensors
UnCLIPPipeline
Model card Files Community
10
patrickvonplaten commited on
Commit
d7b62eb
•
1 Parent(s): fc96d68

upload checkpoint

Browse files
Files changed (20) hide show
  1. decoder/config.json +44 -0
  2. decoder/diffusion_pytorch_model.bin +3 -0
  3. decoder_scheduler/scheduler_config.json +9 -0
  4. model_index.json +44 -0
  5. prior/config.json +11 -0
  6. prior/diffusion_pytorch_model.bin +3 -0
  7. prior_scheduler/scheduler_config.json +9 -0
  8. super_res_first/config.json +38 -0
  9. super_res_first/diffusion_pytorch_model.bin +3 -0
  10. super_res_last/config.json +38 -0
  11. super_res_last/diffusion_pytorch_model.bin +3 -0
  12. super_res_scheduler/scheduler_config.json +9 -0
  13. text_encoder/config.json +25 -0
  14. text_encoder/pytorch_model.bin +3 -0
  15. text_proj/config.json +8 -0
  16. text_proj/diffusion_pytorch_model.bin +3 -0
  17. tokenizer/merges.txt +0 -0
  18. tokenizer/special_tokens_map.json +24 -0
  19. tokenizer/tokenizer_config.json +35 -0
  20. tokenizer/vocab.json +0 -0
decoder/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 64,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 960,
10
+ 1280
11
+ ],
12
+ "center_input_sample": false,
13
+ "class_embed_type": "identity",
14
+ "cross_attention_dim": 1536,
15
+ "down_block_types": [
16
+ "ResnetDownsampleBlock2D",
17
+ "SimpleCrossAttnDownBlock2D",
18
+ "SimpleCrossAttnDownBlock2D",
19
+ "SimpleCrossAttnDownBlock2D"
20
+ ],
21
+ "downsample_padding": 1,
22
+ "dual_cross_attention": false,
23
+ "flip_sin_to_cos": true,
24
+ "freq_shift": 0,
25
+ "in_channels": 3,
26
+ "layers_per_block": 3,
27
+ "mid_block_scale_factor": 1,
28
+ "mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
29
+ "norm_eps": 1e-05,
30
+ "norm_num_groups": 32,
31
+ "num_class_embeds": null,
32
+ "only_cross_attention": false,
33
+ "out_channels": 6,
34
+ "resnet_time_scale_shift": "scale_shift",
35
+ "sample_size": 64,
36
+ "up_block_types": [
37
+ "SimpleCrossAttnUpBlock2D",
38
+ "SimpleCrossAttnUpBlock2D",
39
+ "SimpleCrossAttnUpBlock2D",
40
+ "ResnetUpsampleBlock2D"
41
+ ],
42
+ "upcast_attention": false,
43
+ "use_linear_projection": false
44
+ }
decoder/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581e7c4cc9f1f5ecb9d5157cda138794421a035e925742d39bb4160a6f641d41
3
+ size 3542014953
decoder_scheduler/scheduler_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPScheduler",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "clip_sample": true,
5
+ "clip_sample_range": 1.0,
6
+ "num_train_timesteps": 1000,
7
+ "prediction_type": "epsilon",
8
+ "variance_type": "learned_range"
9
+ }
model_index.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPPipeline",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "decoder": [
5
+ "diffusers",
6
+ "UNet2DConditionModel"
7
+ ],
8
+ "decoder_scheduler": [
9
+ "diffusers",
10
+ "UnCLIPScheduler"
11
+ ],
12
+ "prior": [
13
+ "diffusers",
14
+ "PriorTransformer"
15
+ ],
16
+ "prior_scheduler": [
17
+ "diffusers",
18
+ "UnCLIPScheduler"
19
+ ],
20
+ "super_res_first": [
21
+ "diffusers",
22
+ "UNet2DModel"
23
+ ],
24
+ "super_res_last": [
25
+ "diffusers",
26
+ "UNet2DModel"
27
+ ],
28
+ "super_res_scheduler": [
29
+ "diffusers",
30
+ "UnCLIPScheduler"
31
+ ],
32
+ "text_encoder": [
33
+ "transformers",
34
+ "CLIPTextModelWithProjection"
35
+ ],
36
+ "text_proj": [
37
+ "unclip",
38
+ "UnCLIPTextProjModel"
39
+ ],
40
+ "tokenizer": [
41
+ "transformers",
42
+ "CLIPTokenizer"
43
+ ]
44
+ }
prior/config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PriorTransformer",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "additional_embeddings": 4,
5
+ "attention_head_dim": 64,
6
+ "dropout": 0.0,
7
+ "embedding_dim": 768,
8
+ "num_attention_heads": 32,
9
+ "num_embeddings": 77,
10
+ "num_layers": 20
11
+ }
prior/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d06108745185e3f252f021d4210763538a0814d188e806ea810fec33f83829
3
+ size 4088242781
prior_scheduler/scheduler_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPScheduler",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "clip_sample": true,
5
+ "clip_sample_range": 5.0,
6
+ "num_train_timesteps": 1000,
7
+ "prediction_type": "sample",
8
+ "variance_type": "fixed_small_log"
9
+ }
super_res_first/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "act_fn": "silu",
5
+ "add_attention": false,
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 960,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "down_block_types": [
15
+ "ResnetDownsampleBlock2D",
16
+ "ResnetDownsampleBlock2D",
17
+ "ResnetDownsampleBlock2D",
18
+ "ResnetDownsampleBlock2D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "flip_sin_to_cos": true,
22
+ "freq_shift": 0,
23
+ "in_channels": 6,
24
+ "layers_per_block": 3,
25
+ "mid_block_scale_factor": 1,
26
+ "norm_eps": 1e-05,
27
+ "norm_num_groups": 32,
28
+ "out_channels": 3,
29
+ "resnet_time_scale_shift": "default",
30
+ "sample_size": 256,
31
+ "time_embedding_type": "positional",
32
+ "up_block_types": [
33
+ "ResnetUpsampleBlock2D",
34
+ "ResnetUpsampleBlock2D",
35
+ "ResnetUpsampleBlock2D",
36
+ "ResnetUpsampleBlock2D"
37
+ ]
38
+ }
super_res_first/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5e6b1991ebc9a298f59f39caf63bb229dd5a1f08e9827d18b3d9789f54780a
3
+ size 2766464209
super_res_last/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "act_fn": "silu",
5
+ "add_attention": false,
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 960,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "down_block_types": [
15
+ "ResnetDownsampleBlock2D",
16
+ "ResnetDownsampleBlock2D",
17
+ "ResnetDownsampleBlock2D",
18
+ "ResnetDownsampleBlock2D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "flip_sin_to_cos": true,
22
+ "freq_shift": 0,
23
+ "in_channels": 6,
24
+ "layers_per_block": 3,
25
+ "mid_block_scale_factor": 1,
26
+ "norm_eps": 1e-05,
27
+ "norm_num_groups": 32,
28
+ "out_channels": 3,
29
+ "resnet_time_scale_shift": "default",
30
+ "sample_size": null,
31
+ "time_embedding_type": "positional",
32
+ "up_block_types": [
33
+ "ResnetUpsampleBlock2D",
34
+ "ResnetUpsampleBlock2D",
35
+ "ResnetUpsampleBlock2D",
36
+ "ResnetUpsampleBlock2D"
37
+ ]
38
+ }
super_res_last/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbbb545152758458338f11b93370b97b827da53aa6c737b886b16dd39bae2e9
3
+ size 2766464209
super_res_scheduler/scheduler_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPScheduler",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "clip_sample": true,
5
+ "clip_sample_range": 1.0,
6
+ "num_train_timesteps": 1000,
7
+ "prediction_type": "epsilon",
8
+ "variance_type": "fixed_small_log"
9
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
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
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.26.0.dev0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f5bcf101dde33d8ab9f7e5e1678339fa4258ea07bc65e6ca66e01f9de99622
3
+ size 494664885
text_proj/config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UnCLIPTextProjModel",
3
+ "_diffusers_version": "0.11.0.dev0",
4
+ "clip_embeddings_dim": 768,
5
+ "clip_extra_context_tokens": 4,
6
+ "cross_attention_dim": 1536,
7
+ "time_embed_dim": 1280
8
+ }
text_proj/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb2a8b13658892e3a45bbcb218028a445bb4946bfcb6e5e1b6b0c405d562482
3
+ size 31516932
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "device_map": "auto",
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "name_or_path": "openai/clip-vit-large-patch14",
24
+ "pad_token": "!",
25
+ "special_tokens_map_file": "./special_tokens_map.json",
26
+ "tokenizer_class": "CLIPTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff