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: SG161222/RealVisXL_V3.0
+library_name: diffusers
+license: openrail++
+inference: true
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+---
+
+<!-- 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/EAS4
+
+These are AlignNet weights trained on SG161222/RealVisXL_V3.0 with Pose, Expression and Sparse landmark conditions.
+You can find some example images below.
+
+prompt: photo of a human
+![images_0)](./images_0.png)
+prompt: A render of a head of Disney character
+![images_1)](./images_1.png)
+prompt: a FHD head of an Orc
+![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]

checkpoint-10000/controlnet/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
+}

checkpoint-10000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add37593167dea0af82a79aa37de3afe1bde5fc18797528aabd3ad7b25eccb5c
+size 5728566088

checkpoint-10000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab4f60fe104a68f1b97d9828bce629d0ee88248ce390059cb1c8e05f03ca9fd
+size 11148832787

checkpoint-10000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c32b8b4a4a7aa98c9e47adc6aea0148db23c566a80edccb9b73d6337e27b3ca
+size 14663

checkpoint-10000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be2ad76dcbc923b00e6a142f6db62aad4a46c47bb83864ccb68ddc899d0ce78
+size 557

checkpoint-10000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bcd4cb37625cab1478c5f801ecf8dcfe8513c2acdf383cd99f5bc953b5e8a3
+size 563

checkpoint-20000/controlnet/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
+}

checkpoint-20000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8222cf32805139319bf793e3c3c946ce9a8cb00241cadab4b42cb58ddb7f7c28
+size 5728566088

checkpoint-20000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3994ec56ea240cd06d70577b1972f2cada82362898b48986356635c9a78b5f0
+size 11148832787

checkpoint-20000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc799d32828d7f9ad584044d908f69a6b5e40d1754bf3e6ee689013b7ddcc877
+size 14663

checkpoint-20000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b9bf263b51eb06fdec996c553d4e641e9c9b063d426e12917941ce2c84c056
+size 557

checkpoint-20000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a52968e4da30486ecb0df985c3c21945f186911a08c50d5b944a23ddff433d
+size 563

checkpoint-30000/controlnet/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
+}

checkpoint-30000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc067038cd21235266cfd3a8b8358ccce23312a45b17bb4e584a68d2883adf5
+size 5728566088

checkpoint-30000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46cc8f488419816c4834c5ff90d84c2804c11bdedaa2f539fbe6525492f503c
+size 11148832787

checkpoint-30000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc914fe9cf3fceed3f4b8e4fee40855085efdb0cb8a41a2d57756b7f39df9dc4
+size 14663

checkpoint-30000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f19804b72935a3d0c848c4a10f9b8d94c4a215e6cb6ae7cedd6357f1bc4600b
+size 557

checkpoint-30000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e413f00c8696f8d849f51c390d8fa9ef8d93fd61b9bfab3401aa0e2a1f917546
+size 563

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:bff2dca3f8a72d956f5beff71dd9eccbd964287df771f674d001c6ba27729502
+size 5728566088

logs/EAS4/1744632745.7546809/events.out.tfevents.1744632745.workspace-aph5qbba0n3l-0.2055.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee8b8acf79d327c1a6f8c35a7872b4aeb3ab7a22bf4bf0ed571773a05560b48
+size 2595

logs/EAS4/1744632745.7561772/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: 10000
+checkpoints_total_limit: null
+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/EAS_data2
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: true
+exp_column: exp
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+lmk_column: pred_landmark
+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: 32500
+mixed_precision: fp16
+num_train_epochs: 13
+num_validation_lmks: 4
+output_dir: EAS4
+pose_column: rotation
+pretrained_model_name_or_path: SG161222/RealVisXL_V3.0
+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: EAS4
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 5000
+variant: null

logs/EAS4/events.out.tfevents.1744632745.workspace-aph5qbba0n3l-0.2055.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a832eb28974b84bffd7a72341a836fa8bacbd140e3872b9398ee802f9410d5ba
+size 24246468