End of training
Browse files- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-2500/unet/config.json +68 -0
- checkpoint-2500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2500/unet_ema/config.json +75 -0
- checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-3000/unet/config.json +68 -0
- checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/unet_ema/config.json +75 -0
- checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- logs/text2image-fine-tune/1730072866.6577718/events.out.tfevents.1730072866.IPEG-WS-008.21260.1 +3 -0
- logs/text2image-fine-tune/1730072866.6947837/hparams.yml +55 -0
- logs/text2image-fine-tune/1730073089.0494921/events.out.tfevents.1730073089.IPEG-WS-008.18144.1 +3 -0
- logs/text2image-fine-tune/1730073089.0918372/hparams.yml +55 -0
- logs/text2image-fine-tune/events.out.tfevents.1730072866.IPEG-WS-008.21260.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1730073089.IPEG-WS-008.18144.0 +3 -0
- unet/diffusion_pytorch_model.safetensors +1 -1
- val_imgs_grid.png +0 -0
checkpoint-2500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffe6385d8a76688a1d2ccb46bbe9c30fffbf575af9bfea2d8b92b9f1f1bce84e
|
| 3 |
+
size 6876750164
|
checkpoint-2500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9d915da7f02a86e31ee6f75b8849f0950863ba8994f67a7fc9e9194e604c03e
|
| 3 |
+
size 14408
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2abcdcf339ec48efe17ec29ff331c8a500302e54c8dc37756e2c01a35c6025f4
|
| 3 |
+
size 988
|
checkpoint-2500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a49c4a26f62f0aa84f4b656eef4c3465103beed2061780e76c86467dbea981
|
| 3 |
+
size 1000
|
checkpoint-2500/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/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 |
+
}
|
checkpoint-2500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e416d3f63a01d1690f5b5fc995ca8b4de4c7b4bd338850b62598b49f3e0b947a
|
| 3 |
+
size 3438167536
|
checkpoint-2500/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/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 |
+
"decay": 0.9999,
|
| 25 |
+
"down_block_types": [
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"DownBlock2D"
|
| 30 |
+
],
|
| 31 |
+
"downsample_padding": 1,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dual_cross_attention": false,
|
| 34 |
+
"encoder_hid_dim": null,
|
| 35 |
+
"encoder_hid_dim_type": null,
|
| 36 |
+
"flip_sin_to_cos": true,
|
| 37 |
+
"freq_shift": 0,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"inv_gamma": 1.0,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 44 |
+
"min_decay": 0.0,
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"norm_num_groups": 32,
|
| 47 |
+
"num_attention_heads": null,
|
| 48 |
+
"num_class_embeds": null,
|
| 49 |
+
"only_cross_attention": false,
|
| 50 |
+
"optimization_step": 2500,
|
| 51 |
+
"out_channels": 4,
|
| 52 |
+
"power": 0.6666666666666666,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"update_after_step": 0,
|
| 73 |
+
"use_ema_warmup": false,
|
| 74 |
+
"use_linear_projection": false
|
| 75 |
+
}
|
checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d303a986868bb1669669824555d32dc7c570cb93cc0c5246b1a2cf933ad35cf6
|
| 3 |
+
size 3438167536
|
checkpoint-3000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae99e0b8f5f1f60ce1a9006dbf2f7ec9fd98eb84cfbec0bfc7bd55434153b4b7
|
| 3 |
+
size 6876750164
|
checkpoint-3000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96e3020305e5f7def3f4f8486056afad3a29127a881e8b01294ef39b1a59b78b
|
| 3 |
+
size 14408
|
checkpoint-3000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a69396ad64f717c1fe9ac5ae1dc4b1de2873fe7d50a35b2ee41044e4ffdfc3d
|
| 3 |
+
size 988
|
checkpoint-3000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cd157c3e520fe67f80ed2bb1dc152730c79b5ece6a75d207b88cbe9517b4bf7
|
| 3 |
+
size 1000
|
checkpoint-3000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/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 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:495c7cf4d59488e75c91360559bd8b9b2e99de21300c50db482985810051c98a
|
| 3 |
+
size 3438167536
|
checkpoint-3000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/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 |
+
"decay": 0.9999,
|
| 25 |
+
"down_block_types": [
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"DownBlock2D"
|
| 30 |
+
],
|
| 31 |
+
"downsample_padding": 1,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dual_cross_attention": false,
|
| 34 |
+
"encoder_hid_dim": null,
|
| 35 |
+
"encoder_hid_dim_type": null,
|
| 36 |
+
"flip_sin_to_cos": true,
|
| 37 |
+
"freq_shift": 0,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"inv_gamma": 1.0,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 44 |
+
"min_decay": 0.0,
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"norm_num_groups": 32,
|
| 47 |
+
"num_attention_heads": null,
|
| 48 |
+
"num_class_embeds": null,
|
| 49 |
+
"only_cross_attention": false,
|
| 50 |
+
"optimization_step": 3000,
|
| 51 |
+
"out_channels": 4,
|
| 52 |
+
"power": 0.6666666666666666,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"update_after_step": 0,
|
| 73 |
+
"use_ema_warmup": false,
|
| 74 |
+
"use_linear_projection": false
|
| 75 |
+
}
|
checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52899fbeea249abae4130e5fc0cc69337da1cce17cffda3d783d6775fe2f393f
|
| 3 |
+
size 3438167536
|
logs/text2image-fine-tune/1730072866.6577718/events.out.tfevents.1730072866.IPEG-WS-008.21260.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeed22324bcb8baa8ee680485ce253ad5050c189c968f8b625c48764132309e0
|
| 3 |
+
size 2527
|
logs/text2image-fine-tune/1730072866.6947837/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: null
|
| 7 |
+
caption_column: caption
|
| 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: Trkkk/hannover_text_img
|
| 14 |
+
dream_detail_preservation: 1.0
|
| 15 |
+
dream_training: false
|
| 16 |
+
enable_xformers_memory_efficient_attention: false
|
| 17 |
+
foreach_ema: false
|
| 18 |
+
gradient_accumulation_steps: 4
|
| 19 |
+
gradient_checkpointing: true
|
| 20 |
+
hub_model_id: Trkkk/stable_diffusion
|
| 21 |
+
hub_token: null
|
| 22 |
+
image_column: image
|
| 23 |
+
input_perturbation: 0
|
| 24 |
+
learning_rate: 1.0e-05
|
| 25 |
+
local_rank: -1
|
| 26 |
+
logging_dir: logs
|
| 27 |
+
lr_scheduler: constant
|
| 28 |
+
lr_warmup_steps: 0
|
| 29 |
+
max_grad_norm: 1.0
|
| 30 |
+
max_train_samples: null
|
| 31 |
+
max_train_steps: 3000
|
| 32 |
+
mixed_precision: fp16
|
| 33 |
+
noise_offset: 0
|
| 34 |
+
non_ema_revision: null
|
| 35 |
+
num_train_epochs: 108
|
| 36 |
+
offload_ema: false
|
| 37 |
+
output_dir: ./fine_tuned_model_v4
|
| 38 |
+
prediction_type: null
|
| 39 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 40 |
+
push_to_hub: false
|
| 41 |
+
random_flip: true
|
| 42 |
+
report_to: tensorboard
|
| 43 |
+
resolution: 256
|
| 44 |
+
resume_from_checkpoint: null
|
| 45 |
+
revision: null
|
| 46 |
+
scale_lr: false
|
| 47 |
+
seed: null
|
| 48 |
+
snr_gamma: null
|
| 49 |
+
tracker_project_name: text2image-fine-tune
|
| 50 |
+
train_batch_size: 1
|
| 51 |
+
train_data_dir: null
|
| 52 |
+
use_8bit_adam: false
|
| 53 |
+
use_ema: true
|
| 54 |
+
validation_epochs: 5
|
| 55 |
+
variant: null
|
logs/text2image-fine-tune/1730073089.0494921/events.out.tfevents.1730073089.IPEG-WS-008.18144.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de47fd277a0e3a7bea37703ee94d62e976fedb3977361d8ab71172e37bd84f1a
|
| 3 |
+
size 2527
|
logs/text2image-fine-tune/1730073089.0918372/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: null
|
| 7 |
+
caption_column: caption
|
| 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: Trkkk/hannover_text_img
|
| 14 |
+
dream_detail_preservation: 1.0
|
| 15 |
+
dream_training: false
|
| 16 |
+
enable_xformers_memory_efficient_attention: false
|
| 17 |
+
foreach_ema: false
|
| 18 |
+
gradient_accumulation_steps: 4
|
| 19 |
+
gradient_checkpointing: true
|
| 20 |
+
hub_model_id: Trkkk/stable_diffusion
|
| 21 |
+
hub_token: null
|
| 22 |
+
image_column: image
|
| 23 |
+
input_perturbation: 0
|
| 24 |
+
learning_rate: 1.0e-05
|
| 25 |
+
local_rank: -1
|
| 26 |
+
logging_dir: logs
|
| 27 |
+
lr_scheduler: constant
|
| 28 |
+
lr_warmup_steps: 0
|
| 29 |
+
max_grad_norm: 1.0
|
| 30 |
+
max_train_samples: null
|
| 31 |
+
max_train_steps: 3000
|
| 32 |
+
mixed_precision: fp16
|
| 33 |
+
noise_offset: 0
|
| 34 |
+
non_ema_revision: null
|
| 35 |
+
num_train_epochs: 108
|
| 36 |
+
offload_ema: false
|
| 37 |
+
output_dir: ./fine_tuned_model_v4
|
| 38 |
+
prediction_type: null
|
| 39 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 40 |
+
push_to_hub: true
|
| 41 |
+
random_flip: true
|
| 42 |
+
report_to: tensorboard
|
| 43 |
+
resolution: 256
|
| 44 |
+
resume_from_checkpoint: null
|
| 45 |
+
revision: null
|
| 46 |
+
scale_lr: false
|
| 47 |
+
seed: null
|
| 48 |
+
snr_gamma: null
|
| 49 |
+
tracker_project_name: text2image-fine-tune
|
| 50 |
+
train_batch_size: 1
|
| 51 |
+
train_data_dir: null
|
| 52 |
+
use_8bit_adam: false
|
| 53 |
+
use_ema: true
|
| 54 |
+
validation_epochs: 5
|
| 55 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1730072866.IPEG-WS-008.21260.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e77338f9e3cc2f54236d0369b1a1b2682edfd4d35e0c376b655490a9b475fac
|
| 3 |
+
size 1432
|
logs/text2image-fine-tune/events.out.tfevents.1730073089.IPEG-WS-008.18144.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:249ee64f3d2ef325ecc9702b82704de992603ba7399695aac733614d1cf99cf0
|
| 3 |
+
size 9505698
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3438167536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52899fbeea249abae4130e5fc0cc69337da1cce17cffda3d783d6775fe2f393f
|
| 3 |
size 3438167536
|
val_imgs_grid.png
CHANGED
|
|