End of training

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images_0.png filter=lfs diff=lfs merge=lfs -text
+images_1.png filter=lfs diff=lfs merge=lfs -text
+images_2.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+library_name: diffusers
+license: openrail++
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+inference: true
+---
+
+<!-- This model card has been generated automatically according to the information the training script had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+
+# controlnet-kwanY/PosLmkExp
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
+You can find some example images below.
+
+prompt: a man standing in a field
+![images_0)](./images_0.png)
+prompt: a 3d model of a man in a purple shirt
+![images_1)](./images_1.png)
+prompt: a FHD photo of an Orc face
+![images_2)](./images_2.png)
+
+
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+# TODO: add an example code snippet for running this diffusion pipeline
+```
+
+#### Limitations and bias
+
+[TODO: provide examples of latent issues and potential remediations]
+
+## Training details
+
+[TODO: describe the data used to train the model]

config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "AlignNet",
+  "_diffusers_version": "0.30.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94797b72753cbf337319e3d8f79f2372575bfafaf933c84f3d7566f48ee73276
+size 5042401080

logs/PosLmkExp/1724168671.444537/events.out.tfevents.1724168671.workspace-fsi88u3cxa8k-0.2440.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f9ac84dd5b3693708c2e30409b3b60210212f266900ad026ec6a7ae9181e58
+size 2606

logs/PosLmkExp/1724168671.4465418/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724168823.185757/events.out.tfevents.1724168823.workspace-fsi88u3cxa8k-0.2570.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624d7fc5fc7ca45efca0347dbde053e794f10310934780e535aa45559ec0d90d
+size 2606

logs/PosLmkExp/1724168823.187694/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724168992.7182324/events.out.tfevents.1724168992.workspace-fsi88u3cxa8k-0.2697.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f72ed812e11648c9bb58386aaa2fb4805f9985a92870b30691c847b4d67250
+size 2606

logs/PosLmkExp/1724168992.720203/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724169124.4557145/events.out.tfevents.1724169124.workspace-fsi88u3cxa8k-0.2824.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543dd082dee04a4eff5dd14234fbf5e892ff9fa403b2093fcf4d9c95a368e82e
+size 2606

logs/PosLmkExp/1724169124.4576936/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724169271.6752357/events.out.tfevents.1724169271.workspace-fsi88u3cxa8k-0.2950.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f131b7f365a0a90b95a550745b865ff0b5a49d20e0a1ca33851558647ebd47
+size 2606

logs/PosLmkExp/1724169271.6772501/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724169403.2155008/events.out.tfevents.1724169403.workspace-fsi88u3cxa8k-0.3077.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08a7282c6e7de2ba1ed47bfef9bb96b7335b9ed2eb8d0d0bffd5ed9a87af4de
+size 2606

logs/PosLmkExp/1724169403.2174807/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/1724169475.1445258/events.out.tfevents.1724169475.workspace-fsi88u3cxa8k-0.3195.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22efd5766d007dc7e3dda557ed97efd40c1a4c8465af708bde998e8da913e56
+size 2606

logs/PosLmkExp/1724169475.1464162/hparams.yml

@@ -0,0 +1,56 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: ./cache
+caption_column: image_caption
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: spiga_seg
+controlnet_model_name_or_path: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: kwanY/ExpLmkPos
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: image_exp
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: fp16
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: PosLmkExp
+pose_column: pose
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: PosLmkExp
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 2000
+variant: null

logs/PosLmkExp/events.out.tfevents.1724168671.workspace-fsi88u3cxa8k-0.2440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0014838292afad4c66bd656f09e6117b96b92f883f62596ffc544ef9f5c6675
+size 40

logs/PosLmkExp/events.out.tfevents.1724168823.workspace-fsi88u3cxa8k-0.2570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4da94e9a5e7ec6a91c33a8cea705ea1ece142af506baa9ed6cc19b1aa9c2744
+size 40

logs/PosLmkExp/events.out.tfevents.1724168992.workspace-fsi88u3cxa8k-0.2697.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7d1b8e1a5549f0e740eb6be3c7bd004b47fcb31966367ddf5b850816d0c0cc
+size 40

logs/PosLmkExp/events.out.tfevents.1724169124.workspace-fsi88u3cxa8k-0.2824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbc5452864138f640dbf8f735815e35aabcf227af11d7339e899ea63061fd7b
+size 40

logs/PosLmkExp/events.out.tfevents.1724169271.workspace-fsi88u3cxa8k-0.2950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731a49bd275c32255ec06e82fb2fcf919734ddf18d6ebf37a171a07be1fc71e5
+size 40

logs/PosLmkExp/events.out.tfevents.1724169403.workspace-fsi88u3cxa8k-0.3077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace89683afe85f23fb5a640e43ff799fa27f49c50ff8e43ffe5cd30e65314e84
+size 40

logs/PosLmkExp/events.out.tfevents.1724169475.workspace-fsi88u3cxa8k-0.3195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5076c6efd1475b5c44f54c823c99ab1902c2ace4cacbc2894b973743887126e
+size 4833837