Brvcket commited on
Commit
96630c6
·
verified ·
1 Parent(s): 2cf0bbc

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .ipynb_checkpoints/image_0-checkpoint.png +0 -0
  2. .ipynb_checkpoints/image_1-checkpoint.png +0 -0
  3. .ipynb_checkpoints/image_2-checkpoint.png +0 -0
  4. .ipynb_checkpoints/image_3-checkpoint.png +0 -0
  5. README.md +50 -0
  6. checkpoint-0/model.safetensors +3 -0
  7. checkpoint-0/optimizer.bin +3 -0
  8. checkpoint-0/random_states_0.pkl +3 -0
  9. checkpoint-0/scaler.pt +3 -0
  10. checkpoint-0/scheduler.bin +3 -0
  11. checkpoint-10/optimizer.bin +3 -0
  12. checkpoint-10/random_states_0.pkl +3 -0
  13. checkpoint-10/scaler.pt +3 -0
  14. checkpoint-10/scheduler.bin +3 -0
  15. checkpoint-10/unet/config.json +73 -0
  16. checkpoint-10/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  17. checkpoint-10/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  18. checkpoint-10/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  19. checkpoint-1000/model.safetensors +3 -0
  20. checkpoint-1000/optimizer.bin +3 -0
  21. checkpoint-1000/random_states_0.pkl +3 -0
  22. checkpoint-1000/scaler.pt +3 -0
  23. checkpoint-1000/scheduler.bin +3 -0
  24. checkpoint-1000/unet/config.json +73 -0
  25. checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  26. checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  27. checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
  28. image_0.png +0 -0
  29. image_1.png +0 -0
  30. image_2.png +0 -0
  31. image_3.png +0 -0
  32. logs/text2image-fine-tune-sdxl/1731332400.8098605/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.1 +3 -0
  33. logs/text2image-fine-tune-sdxl/1731332400.8112276/hparams.yml +58 -0
  34. logs/text2image-fine-tune-sdxl/1731336010.2398946/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.1 +3 -0
  35. logs/text2image-fine-tune-sdxl/1731336010.2415638/hparams.yml +58 -0
  36. logs/text2image-fine-tune-sdxl/1731338666.0457904/events.out.tfevents.1731338666.scene-gen-ai-v4-0.1276.1 +3 -0
  37. logs/text2image-fine-tune-sdxl/1731338666.047378/hparams.yml +58 -0
  38. logs/text2image-fine-tune-sdxl/1731339823.9533772/events.out.tfevents.1731339823.scene-gen-ai-v4-0.1463.1 +3 -0
  39. logs/text2image-fine-tune-sdxl/1731339823.9552855/hparams.yml +58 -0
  40. logs/text2image-fine-tune-sdxl/1731346828.0336745/events.out.tfevents.1731346828.scene-gen-ai-v4-0.2415.1 +3 -0
  41. logs/text2image-fine-tune-sdxl/1731346828.035174/hparams.yml +58 -0
  42. logs/text2image-fine-tune-sdxl/1731352544.2337453/events.out.tfevents.1731352544.scene-gen-ai-v4-0.2709.1 +3 -0
  43. logs/text2image-fine-tune-sdxl/1731352544.2352123/hparams.yml +58 -0
  44. logs/text2image-fine-tune-sdxl/1731361202.666019/events.out.tfevents.1731361202.scene-gen-ai-v4-0.3445.1 +3 -0
  45. logs/text2image-fine-tune-sdxl/1731361202.6674397/hparams.yml +58 -0
  46. logs/text2image-fine-tune-sdxl/1731412552.530759/events.out.tfevents.1731412552.scene-gen-ai-v4-0.4068.1 +3 -0
  47. logs/text2image-fine-tune-sdxl/1731412552.5325375/hparams.yml +58 -0
  48. logs/text2image-fine-tune-sdxl/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.0 +3 -0
  49. logs/text2image-fine-tune-sdxl/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.0 +3 -0
  50. logs/text2image-fine-tune-sdxl/events.out.tfevents.1731338665.scene-gen-ai-v4-0.1276.0 +3 -0
.ipynb_checkpoints/image_0-checkpoint.png ADDED
.ipynb_checkpoints/image_1-checkpoint.png ADDED
.ipynb_checkpoints/image_2-checkpoint.png ADDED
.ipynb_checkpoints/image_3-checkpoint.png ADDED
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers-training
10
+ - diffusers
11
+ - stable-diffusion-xl
12
+ - stable-diffusion-xl-diffusers
13
+ - text-to-image
14
+ - diffusers-training
15
+ - diffusers
16
+ inference: true
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+
23
+ # Text-to-image finetuning - Brvcket/test
24
+
25
+ This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **lambdalabs/naruto-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a cute Sundar Pichai creature:
26
+
27
+ ![img_0](./image_0.png)
28
+ ![img_1](./image_1.png)
29
+ ![img_2](./image_2.png)
30
+ ![img_3](./image_3.png)
31
+
32
+
33
+ Special VAE used for training: None.
34
+
35
+
36
+ ## Intended uses & limitations
37
+
38
+ #### How to use
39
+
40
+ ```python
41
+ # TODO: add an example code snippet for running this diffusion pipeline
42
+ ```
43
+
44
+ #### Limitations and bias
45
+
46
+ [TODO: provide examples of latent issues and potential remediations]
47
+
48
+ ## Training details
49
+
50
+ [TODO: describe the data used to train the model]
checkpoint-0/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40582c2d826aff7528a3b25e76530d6cdb519d40573d149385db652bb6794a95
3
+ size 10270077736
checkpoint-0/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:146470be27b80427b65c56a9d5e6bbc1cef34cccf41a14819d08676538ea50f5
3
+ size 20541173449
checkpoint-0/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c05411d9c2fcf51cafe8572e9df7d54eb2a629850a2f3414a0212c3c800076
3
+ size 14727
checkpoint-0/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909ffc5e40adcfcc03f8fb8e8cc5a6605d5aaa37643bab9d485939a891938ae9
3
+ size 557
checkpoint-0/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e44312a25357272b087dbcd9aabcb32e966ed8c4b8f09900e4a4c149043c248
3
+ size 563
checkpoint-10/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a901b5540e1bf09fee7fbf9e18d663f709f6ee7bee0ec6b5984bac7f45fb339
3
+ size 20541173449
checkpoint-10/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f412f47ce76edb6f9f01d64dac30929f3878117870346f7295032bc9ec63c41
3
+ size 14663
checkpoint-10/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e76ebe66a23f043b42182e14294a93d529fdc5c0c08159fd9fc10bbeaad36
3
+ size 557
checkpoint-10/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715829e32fb165fa1a4f8e58725497d96735edca5fca51b555511ac1bfc4ed5a
3
+ size 563
checkpoint-10/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
checkpoint-10/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03d560e86d1e18fccc5e16f5d446c215077beacfc1803ef0a0a0f31ecbb582e
3
+ size 9988139160
checkpoint-10/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad645735ccde3f94efd1c9f456c9b75c0bafbd796329c230ccba1ad91abed43
3
+ size 281938304
checkpoint-10/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c35c6bf0a0f36b2dac76d366f54ae0fe9e0d22b02fd3a7a1ffd8255931930f6
3
+ size 10270077736
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66f6beb23eb8d0f79ac1717b198286815a220dd75b438d826ac3ceb1c5e7f55
3
+ size 20541173449
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201a0dc48092a545be0a353419d4c770d95e0786400c376aebe37112e11fe636
3
+ size 14663
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef4512ee578f7df5b13e2e3b75baf09a7fafaaea150f2fa331e91ea839fc265
3
+ size 557
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db4cf2e94898fdabcf298901aa7b9ecf06ae3b38183fd7ba2cb2e9c7ce68e56
3
+ size 563
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882b6b49e6f7086ac60eb2518159f0f32bc771767ac2f95e8f2086dd1c0e27c7
3
+ size 9988139160
checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3282cffdf120993d63fe2a1e52bbfd1330d13cde2d5dbad804c11da4d62f57b3
3
+ size 281938304
checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/text2image-fine-tune-sdxl/1731332400.8098605/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40cd701d86922e4bc38266e3090afc6774fdf94e8086b6428a43b118cf8c3231
3
+ size 2642
logs/text2image-fine-tune-sdxl/1731332400.8112276/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 10
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1
57
+ validation_prompt: null
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731336010.2398946/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d15a85df5ad4eb66c9b46d6becd4f1f43ec59a1dc6b610142fc46ff91812047
3
+ size 2719
logs/text2image-fine-tune-sdxl/1731336010.2415638/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 10
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 10
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731338666.0457904/events.out.tfevents.1731338666.scene-gen-ai-v4-0.1276.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c241a59ae30bceb1c6284e4cac4db9e832c27da9c82b66bafe0c6eac95cfef7a
3
+ size 2719
logs/text2image-fine-tune-sdxl/1731338666.047378/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 10
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 10
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731339823.9533772/events.out.tfevents.1731339823.scene-gen-ai-v4-0.1463.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8656065ec6100a30f34a313e5cd2a9996cadc43d02011bffc79653a730fcf83c
3
+ size 2719
logs/text2image-fine-tune-sdxl/1731339823.9552855/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1000
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731346828.0336745/events.out.tfevents.1731346828.scene-gen-ai-v4-0.2415.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f37ca231959492f6a970ff9caa36307b442b405f9847dd41db8519cc103df0
3
+ size 2719
logs/text2image-fine-tune-sdxl/1731346828.035174/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1000
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731352544.2337453/events.out.tfevents.1731352544.scene-gen-ai-v4-0.2709.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbca5585ae403bb56839e2b0ddef63bf9dcb107505801e7e4842018b4d63f608
3
+ size 2719
logs/text2image-fine-tune-sdxl/1731352544.2352123/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/naruto-blip-captions
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1000
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731361202.666019/events.out.tfevents.1731361202.scene-gen-ai-v4-0.3445.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf468c28f99cbf36d44cad9018ff364d98489c33f9e407dde7dddbc36b643c2
3
+ size 2707
logs/text2image-fine-tune-sdxl/1731361202.6674397/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Brvcket/sdxl-lights
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1000
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/1731412552.530759/events.out.tfevents.1731412552.scene-gen-ai-v4-0.4068.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83466c78984ab7e46211f0a2239b4df6465be268ae1d1969ae83138c0908f194
3
+ size 2707
logs/text2image-fine-tune-sdxl/1731412552.5325375/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Brvcket/sdxl-lights
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: test
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: false
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: false
56
+ validation_epochs: 1000
57
+ validation_prompt: a cute Sundar Pichai creature
58
+ variant: null
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e0664ed7cfdcacde055ed377ec05084fe8000277a2423ece170e537a4f392a
3
+ size 568
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d79a1a6468549cc4cb7892cda2203c3aae20a008791c7684000ad8f6f12d55
3
+ size 25246
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731338665.scene-gen-ai-v4-0.1276.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c3cfadc3f271e245984ab9a7fb8378b29b580cfc8e06dfbc730755ccc2a4cd
3
+ size 88