End of training

README.md

@@ -0,0 +1,39 @@
+---
+base_model: Brvcket/stable-outpainting-xl-0.1
+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-Brvcket/stable-outpainting-xl-lights-0.2
+
+These are controlnet weights trained on Brvcket/stable-outpainting-xl-0.1 with new type of conditioning.
+
+
+
+## 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-5000/controlnet/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "alimama-creative/EcomXL_controlnet_inpaint",
+  "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-5000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a237b69bee6e64f30ca5436435e8d78f995c2b6506d613089a10ee3b013cc1f
+size 5004167864

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f0ae16be74516e620e5fbb679d15fbdb45e7cf51f8d70a361f411511e4576f
+size 10008840997

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c13d0ba6a6822347fdaed9c3faeabbb8af8ee9c8b6fc0184252edef0d6a7a67
+size 14599

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41313b6733b65c1acca917a7c2ced06503c11b898e6cd5de1e6a9f13bfb54ef
+size 557

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240578dc19fc27ef2ac9d5b4920e97b1d1064e3249bbe58ae29d322c5115b9e0
+size 563

config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "alimama-creative/EcomXL_controlnet_inpaint",
+  "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 sha256:7a237b69bee6e64f30ca5436435e8d78f995c2b6506d613089a10ee3b013cc1f
+size 5004167864

logs/sd_xl_train_controlnet/1728903853.8703887/events.out.tfevents.1728903853.scene-gen-ai-v2-0.16685.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0a1e1c41749b75bb7f01e12b1483b8154a4630d1a7c33515f9d1f762db5bb0
+size 2708

logs/sd_xl_train_controlnet/1728903853.8721006/hparams.yml

@@ -0,0 +1,54 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+caption_column: text
+checkpointing_steps: 5000
+checkpoints_total_limit: null
+conditioning_image_column: conditioning_image
+controlnet_model_name_or_path: alimama-creative/EcomXL_controlnet_inpaint
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Brvcket/stable-outpainting-xl-controlnet-dataset
+enable_npu_flash_attention: false
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 5.0e-06
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 5000
+mixed_precision: fp16
+num_train_epochs: 6
+num_validation_images: 4
+output_dir: stable-outpainting-xl-lights-0.2
+pretrained_model_name_or_path: Brvcket/stable-outpainting-xl-0.1
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: sd_xl_train_controlnet
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 5000
+variant: null

logs/sd_xl_train_controlnet/events.out.tfevents.1728903853.scene-gen-ai-v2-0.16685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b017822ac75f10625826902b298e5c7dcf05fb5d74ceeac6187559d0f8cc9b
+size 419834