Hugging Face's logo

hearmeneigh
/
sd21-e621-rising-v2

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
anthro
furry
e621
nsfw
Not-For-All-Audiences
Model card Files
xet
Metrics Community
4
hearmeneigh commited on
Commit
1462a27
·
1 Parent(s): 787d1f2

End of training

Browse files
Files changed (31) hide show
  1. .gitignore +2 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/random_states_0.pkl +3 -0
  4. checkpoint-1000/scheduler.bin +3 -0
  5. checkpoint-1000/unet/config.json +56 -0
  6. checkpoint-1000/unet/diffusion_pytorch_model.bin +3 -0
  7. checkpoint-1000/unet_ema/config.json +63 -0
  8. checkpoint-1000/unet_ema/diffusion_pytorch_model.bin +3 -0
  9. checkpoint-500/optimizer.bin +3 -0
  10. checkpoint-500/random_states_0.pkl +3 -0
  11. checkpoint-500/scheduler.bin +3 -0
  12. checkpoint-500/unet/config.json +56 -0
  13. checkpoint-500/unet/diffusion_pytorch_model.bin +3 -0
  14. checkpoint-500/unet_ema/config.json +63 -0
  15. checkpoint-500/unet_ema/diffusion_pytorch_model.bin +3 -0
  16. feature_extractor/preprocessor_config.json +28 -0
  17. logs/text2image-fine-tune/1680467399.5389252/events.out.tfevents.1680467399.4e67fc6034e9.1261.1 +3 -0
  18. logs/text2image-fine-tune/1680467399.540434/hparams.yml +47 -0
  19. logs/text2image-fine-tune/events.out.tfevents.1680467399.4e67fc6034e9.1261.0 +3 -0
  20. model_index.json +33 -0
  21. scheduler/scheduler_config.json +14 -0
  22. text_encoder/config.json +25 -0
  23. text_encoder/pytorch_model.bin +3 -0
  24. tokenizer/merges.txt +0 -0
  25. tokenizer/special_tokens_map.json +24 -0
  26. tokenizer/tokenizer_config.json +33 -0
  27. tokenizer/vocab.json +0 -0
  28. unet/config.json +56 -0
  29. unet/diffusion_pytorch_model.bin +3 -0
  30. vae/config.json +31 -0
  31. vae/diffusion_pytorch_model.bin +3 -0
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ step_*
2
+ epoch_*
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4a5380845c8570132a4b431913625ae868c55989e0e08cd390ac61249cf716
3
+ size 6927866927
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0fcad1b52fae2785b416d9df675cc96d00fcae9ceb0410959efef9ff76b52a
3
+ size 19739
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92134480004f14722effb5a8aba3e3b89d1d6b6175645009cf38fca51e7b8b94
3
+ size 563
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
checkpoint-1000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7763863c5758fcbaaa77e975e2345b3037bba20c7d8ed3d7cb3251b3a8a243ce
3
+ size 3463934693
checkpoint-1000/unet_ema/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "decay": 0.9999,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dual_cross_attention": false,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "inv_gamma": 1.0,
36
+ "layers_per_block": 2,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "min_decay": 0.0,
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "optimization_step": 1000,
45
+ "out_channels": 4,
46
+ "power": 0.6666666666666666,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "sample_size": 64,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_type": "positional",
52
+ "timestep_post_act": null,
53
+ "up_block_types": [
54
+ "UpBlock2D",
55
+ "CrossAttnUpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D"
58
+ ],
59
+ "upcast_attention": false,
60
+ "update_after_step": 0,
61
+ "use_ema_warmup": false,
62
+ "use_linear_projection": true
63
+ }
checkpoint-1000/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c872a74feb50cf372fda2abc468a791996bfac4efa6b83aa76a612894b9373
3
+ size 3463925093
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e320c6d441e88847db451760d6dcf77c6ea9d23a2a067df334db45c3a5afa7
3
+ size 6927866927
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caf4da8efd10e7a0ec99c455034f0389bee1f1b53e8f41270d43d49f332d348
3
+ size 19739
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208f40d22310e5f2775339c8e532c79bfc88f8b3d032323ee4575b1b1e52dc28
3
+ size 563
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
checkpoint-500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3d5c8a56fadcb96d67811c30fe322d5695df78746ff44fa4676dd49d62a7bd
3
+ size 3463934693
checkpoint-500/unet_ema/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "decay": 0.9999,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dual_cross_attention": false,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "inv_gamma": 1.0,
36
+ "layers_per_block": 2,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "min_decay": 0.0,
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "optimization_step": 500,
45
+ "out_channels": 4,
46
+ "power": 0.6666666666666666,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "sample_size": 64,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_type": "positional",
52
+ "timestep_post_act": null,
53
+ "up_block_types": [
54
+ "UpBlock2D",
55
+ "CrossAttnUpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D"
58
+ ],
59
+ "upcast_attention": false,
60
+ "update_after_step": 0,
61
+ "use_ema_warmup": false,
62
+ "use_linear_projection": true
63
+ }
checkpoint-500/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e7323fcc4c373bede924e7f11b5d7a27fc2218113ad7034c244641b4b73cdf
3
+ size 3463925093
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
logs/text2image-fine-tune/1680467399.5389252/events.out.tfevents.1680467399.4e67fc6034e9.1261.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11268d9df8fcba291becf779be7762b844b93c8c7541001d9b5b71eb7f23ad4
3
+ size 2336
logs/text2image-fine-tune/1680467399.540434/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: /workspace/huggingface/cache
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: hearmeneigh/e621-rising-v2-curated
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: hearmeneigh/sd21-e621-rising-v2
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 4.0e-06
21
+ local_rank: 0
22
+ logging_dir: logs
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ maintain_aspect_ratio: true
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1400
29
+ mixed_precision: bf16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: /workspace/output/sd2-hmn-v2-step-1
34
+ pretrained_model_name_or_path: hearmeneigh/sd21-e621-rising-v1
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 512
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: null
43
+ shuffle_tags: true
44
+ train_batch_size: 34
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
logs/text2image-fine-tune/events.out.tfevents.1680467399.4e67fc6034e9.1261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb51fa07df4afe39fd3f8fd922a3ec4657321b1fe91f2d5836513ba268064c6
3
+ size 68561
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.14.0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": false,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.14.0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.27.4",
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 sha256:0524bc98778fa7fe9d98454341c788679397b2e0e89a1c7bfa258d9808177183
3
+ size 680904225
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "pad_token": "<|endoftext|>",
23
+ "special_tokens_map_file": "./special_tokens_map.json",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 64,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5b479b48db310d7ab4fc2983e587959a010e3f28d6669730670533d72a482e
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.14.0",
4
+ "_name_or_path": "hearmeneigh/sd21-e621-rising-v1",
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
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 768,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7364df45c07ae1b4c3b96178780a87c370245b919453e9c73ae230707db1c55a
3
+ size 167407601