First model version
Browse files- out_train_text_encoder/checkpoint-600/optimizer.bin +3 -0
- out_train_text_encoder/checkpoint-600/random_states_0.pkl +3 -0
- out_train_text_encoder/checkpoint-600/scheduler.bin +3 -0
- out_train_text_encoder/checkpoint-600/text_encoder/config.json +25 -0
- out_train_text_encoder/checkpoint-600/text_encoder/pytorch_model.bin +3 -0
- out_train_text_encoder/checkpoint-600/unet/config.json +68 -0
- out_train_text_encoder/checkpoint-600/unet/diffusion_pytorch_model.safetensors +3 -0
- out_train_text_encoder/feature_extractor/preprocessor_config.json +28 -0
- out_train_text_encoder/logs/dreambooth/1698654036.898121/events.out.tfevents.1698654036.r502n017.2486577.1 +3 -0
- out_train_text_encoder/logs/dreambooth/1698654036.901086/hparams.yml +59 -0
- out_train_text_encoder/logs/dreambooth/events.out.tfevents.1698654036.r502n017.2486577.0 +3 -0
- out_train_text_encoder/model_index.json +34 -0
- out_train_text_encoder/safety_checker/config.json +28 -0
- out_train_text_encoder/safety_checker/model.safetensors +3 -0
- out_train_text_encoder/scheduler/scheduler_config.json +15 -0
- out_train_text_encoder/text_encoder/config.json +25 -0
- out_train_text_encoder/text_encoder/model.safetensors +3 -0
- out_train_text_encoder/tokenizer/merges.txt +0 -0
- out_train_text_encoder/tokenizer/special_tokens_map.json +24 -0
- out_train_text_encoder/tokenizer/tokenizer_config.json +30 -0
- out_train_text_encoder/tokenizer/vocab.json +0 -0
- out_train_text_encoder/unet/config.json +68 -0
- out_train_text_encoder/unet/diffusion_pytorch_model.safetensors +3 -0
- out_train_text_encoder/vae/config.json +32 -0
- out_train_text_encoder/vae/diffusion_pytorch_model.safetensors +3 -0
out_train_text_encoder/checkpoint-600/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:950c123edf1142729a4db2c9f4ed2367ff10c3a075eb3ca9ef9d130bcfb266cc
|
| 3 |
+
size 1972592405
|
out_train_text_encoder/checkpoint-600/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5725176150dcd449484a866f90ad9518e4aae619db798c53530e8963850cfd0b
|
| 3 |
+
size 14567
|
out_train_text_encoder/checkpoint-600/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d66e52db81db36256ebf35ef15ebb6bb0fbd20c10ac14f32c85108aa8ea2e01
|
| 3 |
+
size 559
|
out_train_text_encoder/checkpoint-600/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-4",
|
| 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": "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": 512,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.34.1",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
out_train_text_encoder/checkpoint-600/text_encoder/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bce86dcc5115176f27609b4c8a1ba7feab9a6463adaeb784848252293f6e03e2
|
| 3 |
+
size 492307065
|
out_train_text_encoder/checkpoint-600/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-4",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280,
|
| 15 |
+
1280
|
| 16 |
+
],
|
| 17 |
+
"center_input_sample": false,
|
| 18 |
+
"class_embed_type": null,
|
| 19 |
+
"class_embeddings_concat": false,
|
| 20 |
+
"conv_in_kernel": 3,
|
| 21 |
+
"conv_out_kernel": 3,
|
| 22 |
+
"cross_attention_dim": 768,
|
| 23 |
+
"cross_attention_norm": null,
|
| 24 |
+
"down_block_types": [
|
| 25 |
+
"CrossAttnDownBlock2D",
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"DownBlock2D"
|
| 29 |
+
],
|
| 30 |
+
"downsample_padding": 1,
|
| 31 |
+
"dropout": 0.0,
|
| 32 |
+
"dual_cross_attention": false,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"in_channels": 4,
|
| 38 |
+
"layers_per_block": 2,
|
| 39 |
+
"mid_block_only_cross_attention": null,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 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 |
+
"reverse_transformer_layers_per_block": null,
|
| 53 |
+
"sample_size": 64,
|
| 54 |
+
"time_cond_proj_dim": null,
|
| 55 |
+
"time_embedding_act_fn": null,
|
| 56 |
+
"time_embedding_dim": null,
|
| 57 |
+
"time_embedding_type": "positional",
|
| 58 |
+
"timestep_post_act": null,
|
| 59 |
+
"transformer_layers_per_block": 1,
|
| 60 |
+
"up_block_types": [
|
| 61 |
+
"UpBlock2D",
|
| 62 |
+
"CrossAttnUpBlock2D",
|
| 63 |
+
"CrossAttnUpBlock2D",
|
| 64 |
+
"CrossAttnUpBlock2D"
|
| 65 |
+
],
|
| 66 |
+
"upcast_attention": false,
|
| 67 |
+
"use_linear_projection": false
|
| 68 |
+
}
|
out_train_text_encoder/checkpoint-600/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:772400764266b8c23297168104377826010cd15d029cd39c73624456a9a91437
|
| 3 |
+
size 3438167536
|
out_train_text_encoder/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 |
+
}
|
out_train_text_encoder/logs/dreambooth/1698654036.898121/events.out.tfevents.1698654036.r502n017.2486577.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bd923d8f7386ec6ef75f36b02731b9e5b2f17753065e57bd1b428eaa2f51ffd
|
| 3 |
+
size 2797
|
out_train_text_encoder/logs/dreambooth/1698654036.901086/hparams.yml
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
center_crop: false
|
| 7 |
+
checkpointing_steps: 600
|
| 8 |
+
checkpoints_total_limit: null
|
| 9 |
+
class_data_dir: dog
|
| 10 |
+
class_labels_conditioning: null
|
| 11 |
+
class_prompt: a photo of dog
|
| 12 |
+
dataloader_num_workers: 0
|
| 13 |
+
enable_xformers_memory_efficient_attention: false
|
| 14 |
+
gradient_accumulation_steps: 1
|
| 15 |
+
gradient_checkpointing: false
|
| 16 |
+
hub_model_id: null
|
| 17 |
+
hub_token: null
|
| 18 |
+
instance_data_dir: dog
|
| 19 |
+
instance_prompt: a photo of sks dog
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lr_num_cycles: 1
|
| 24 |
+
lr_power: 1.0
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 0
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_steps: 800
|
| 29 |
+
mixed_precision: null
|
| 30 |
+
num_class_images: 200
|
| 31 |
+
num_train_epochs: 4
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
offset_noise: false
|
| 34 |
+
output_dir: out_train_text_encoder
|
| 35 |
+
pre_compute_text_embeddings: false
|
| 36 |
+
pretrained_model_name_or_path: stable-diffusion-v1-4
|
| 37 |
+
prior_generation_precision: null
|
| 38 |
+
prior_loss_weight: 1.0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 512
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
sample_batch_size: 4
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
set_grads_to_none: false
|
| 48 |
+
skip_save_text_encoder: false
|
| 49 |
+
snr_gamma: null
|
| 50 |
+
text_encoder_use_attention_mask: false
|
| 51 |
+
tokenizer_max_length: null
|
| 52 |
+
tokenizer_name: null
|
| 53 |
+
train_batch_size: 1
|
| 54 |
+
train_text_encoder: true
|
| 55 |
+
use_8bit_adam: true
|
| 56 |
+
validation_prompt: null
|
| 57 |
+
validation_scheduler: DPMSolverMultistepScheduler
|
| 58 |
+
validation_steps: 100
|
| 59 |
+
with_prior_preservation: true
|
out_train_text_encoder/logs/dreambooth/events.out.tfevents.1698654036.r502n017.2486577.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fb829209d36b332eb146d076df93af32dd5c8945c217fc43d29015e63c1da35
|
| 3 |
+
size 66986
|
out_train_text_encoder/model_index.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableDiffusionPipeline",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-4",
|
| 5 |
+
"feature_extractor": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"CLIPImageProcessor"
|
| 8 |
+
],
|
| 9 |
+
"requires_safety_checker": true,
|
| 10 |
+
"safety_checker": [
|
| 11 |
+
"stable_diffusion",
|
| 12 |
+
"StableDiffusionSafetyChecker"
|
| 13 |
+
],
|
| 14 |
+
"scheduler": [
|
| 15 |
+
"diffusers",
|
| 16 |
+
"PNDMScheduler"
|
| 17 |
+
],
|
| 18 |
+
"text_encoder": [
|
| 19 |
+
"transformers",
|
| 20 |
+
"CLIPTextModel"
|
| 21 |
+
],
|
| 22 |
+
"tokenizer": [
|
| 23 |
+
"transformers",
|
| 24 |
+
"CLIPTokenizer"
|
| 25 |
+
],
|
| 26 |
+
"unet": [
|
| 27 |
+
"diffusers",
|
| 28 |
+
"UNet2DConditionModel"
|
| 29 |
+
],
|
| 30 |
+
"vae": [
|
| 31 |
+
"diffusers",
|
| 32 |
+
"AutoencoderKL"
|
| 33 |
+
]
|
| 34 |
+
}
|
out_train_text_encoder/safety_checker/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-4/safety_checker",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"StableDiffusionSafetyChecker"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 768,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"dropout": 0.0,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"model_type": "clip_text_model",
|
| 15 |
+
"num_attention_heads": 12
|
| 16 |
+
},
|
| 17 |
+
"torch_dtype": "float32",
|
| 18 |
+
"transformers_version": "4.34.1",
|
| 19 |
+
"vision_config": {
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"hidden_size": 1024,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"model_type": "clip_vision_model",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 24,
|
| 26 |
+
"patch_size": 14
|
| 27 |
+
}
|
| 28 |
+
}
|
out_train_text_encoder/safety_checker/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
| 3 |
+
size 1215979664
|
out_train_text_encoder/scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "PNDMScheduler",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 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 |
+
"timestep_spacing": "leading",
|
| 14 |
+
"trained_betas": null
|
| 15 |
+
}
|
out_train_text_encoder/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-4",
|
| 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": "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": 512,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.34.1",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
out_train_text_encoder/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5f769d5af38f5e5f82c98b1457bf542d35ecde762884647054d3a3e7267978
|
| 3 |
+
size 492265168
|
out_train_text_encoder/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
out_train_text_encoder/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": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
out_train_text_encoder/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": true,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 77,
|
| 27 |
+
"pad_token": "<|endoftext|>",
|
| 28 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>"
|
| 30 |
+
}
|
out_train_text_encoder/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
out_train_text_encoder/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-4",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280,
|
| 15 |
+
1280
|
| 16 |
+
],
|
| 17 |
+
"center_input_sample": false,
|
| 18 |
+
"class_embed_type": null,
|
| 19 |
+
"class_embeddings_concat": false,
|
| 20 |
+
"conv_in_kernel": 3,
|
| 21 |
+
"conv_out_kernel": 3,
|
| 22 |
+
"cross_attention_dim": 768,
|
| 23 |
+
"cross_attention_norm": null,
|
| 24 |
+
"down_block_types": [
|
| 25 |
+
"CrossAttnDownBlock2D",
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"DownBlock2D"
|
| 29 |
+
],
|
| 30 |
+
"downsample_padding": 1,
|
| 31 |
+
"dropout": 0.0,
|
| 32 |
+
"dual_cross_attention": false,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"in_channels": 4,
|
| 38 |
+
"layers_per_block": 2,
|
| 39 |
+
"mid_block_only_cross_attention": null,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 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 |
+
"reverse_transformer_layers_per_block": null,
|
| 53 |
+
"sample_size": 64,
|
| 54 |
+
"time_cond_proj_dim": null,
|
| 55 |
+
"time_embedding_act_fn": null,
|
| 56 |
+
"time_embedding_dim": null,
|
| 57 |
+
"time_embedding_type": "positional",
|
| 58 |
+
"timestep_post_act": null,
|
| 59 |
+
"transformer_layers_per_block": 1,
|
| 60 |
+
"up_block_types": [
|
| 61 |
+
"UpBlock2D",
|
| 62 |
+
"CrossAttnUpBlock2D",
|
| 63 |
+
"CrossAttnUpBlock2D",
|
| 64 |
+
"CrossAttnUpBlock2D"
|
| 65 |
+
],
|
| 66 |
+
"upcast_attention": false,
|
| 67 |
+
"use_linear_projection": false
|
| 68 |
+
}
|
out_train_text_encoder/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c31f0e912eda8c8e329fe2ac8b575029340998b9bfb1e50cdc5d36999e1a9aa9
|
| 3 |
+
size 3438167536
|
out_train_text_encoder/vae/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.22.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-4/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": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 4,
|
| 21 |
+
"layers_per_block": 2,
|
| 22 |
+
"norm_num_groups": 32,
|
| 23 |
+
"out_channels": 3,
|
| 24 |
+
"sample_size": 512,
|
| 25 |
+
"scaling_factor": 0.18215,
|
| 26 |
+
"up_block_types": [
|
| 27 |
+
"UpDecoderBlock2D",
|
| 28 |
+
"UpDecoderBlock2D",
|
| 29 |
+
"UpDecoderBlock2D",
|
| 30 |
+
"UpDecoderBlock2D"
|
| 31 |
+
]
|
| 32 |
+
}
|
out_train_text_encoder/vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
|
| 3 |
+
size 334643268
|