ptx0 commited on
Commit
9135a79
1 Parent(s): 9fa10ee

13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data)

Browse files
config.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
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
+ }
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.17.0.dev0",
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
+ "DDIMScheduler"
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": false,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "trained_betas": null
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/notebooks/images/datasets/models//checkpoint-13000/text_encoder",
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": "float32",
23
+ "transformers_version": "4.29.2",
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 sha256:03c3477c3db2f7edb53d631293d9a7018c4b0a23cee490b60cb049aa9bd54e95
3
+ size 1361679905
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
+ "clean_up_tokenization_spaces": true,
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
+ "pad_token": "<|endoftext|>",
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "/notebooks/images/datasets/models//checkpoint-13000/unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "sample_size": 96,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "up_block_types": [
59
+ "UpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D"
63
+ ],
64
+ "upcast_attention": true,
65
+ "use_linear_projection": true
66
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6636f688759f6b44b8d332ec0a6fc513cba59c49240d4170f45b8579d2071e6f
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/845609e6cf0a060d8cd837297e5c169df5bff72c/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
+ "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 sha256:185b0c03485b4048bb6158de087df301b79ea187844c76ae91cd4cda207282a2
3
+ size 334715569