End of training

README.md

@@ -0,0 +1,79 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- diffusers-training
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: '<s0><s1> style'
+        
+base_model: stabilityai/stable-diffusion-xl
+instance_prompt: <s0><s1> style
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - busetolunay/ace2
+
+<Gallery />
+
+## Model description
+
+### These are busetolunay/ace2 LoRA adaption weights for stabilityai/stable-diffusion-xl.
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`ace2.safetensors` here 💾](/busetolunay/ace2/blob/main/ace2.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:ace2:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+- *Embeddings*: download **[`ace2_emb.safetensors` here 💾](/busetolunay/ace2/blob/main/ace2_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `ace2_emb` to your prompt. For example, `ace2_emb style`
+    (you need both the LoRA and the embeddings as they were trained together for this LoRA)
+    
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+        
+pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('busetolunay/ace2', weight_name='pytorch_lora_weights.safetensors')
+embedding_path = hf_hub_download(repo_id='busetolunay/ace2', filename='ace2_emb.safetensors', repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
+pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
+        
+image = pipeline('<s0><s1> style').images[0]
+```
+
+For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
+
+## Trigger words
+
+To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
+
+to trigger concept `a0ce` → use `<s0><s1>` in your prompt 
+
+
+
+## Details
+All [Files & versions](/busetolunay/ace2/tree/main).
+
+The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
+
+LoRA for the text encoder was enabled. False.
+
+Pivotal tuning was enabled: True.
+
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
+
+

ace2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce39829bc373b040309bfc52e4e85820281448c927b56bcbd57f6f2d18dfbb5
+size 186046568

ace2_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf625eae9290bed295a5dcf45f1cfa6e85a5a86ba607fb2caee54930f3cd02f3
+size 16536

logs/dreambooth-lora-sd-xl/1724832769.3423722/events.out.tfevents.1724832769.3273fd9608c9.1994.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4793454fae688b9198e18e530c8f015d138cdd43704102a3ea547b986502011f
+size 3729

logs/dreambooth-lora-sd-xl/1724832769.3555667/hparams.yml

@@ -0,0 +1,79 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+adam_weight_decay_text_encoder: 0.01
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: text
+center_crop: false
+checkpointing_steps: 10000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+clip_skip: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: busetolunay/deneme_building
+do_edm_style_training: false
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: busetolunay/ace2
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: <s0><s1> style
+learning_rate: 1.0
+local_rank: 0
+logging_dir: logs
+lora_unet_blocks: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_steps: 1500
+mixed_precision: bf16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 215
+num_validation_images: 4
+optimizer: prodigy
+output_dir: ace2
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+prior_generation_precision: null
+prior_loss_weight: 1.0
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 128
+repeats: 1
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+snr_gamma: 5.0
+text_encoder_lr: 1.0
+token_abstraction: a0ce
+train_batch_size: 1
+train_text_encoder: false
+train_text_encoder_frac: 1.0
+train_text_encoder_ti: true
+train_text_encoder_ti_frac: 0.5
+use_8bit_adam: false
+use_blora: false
+use_dora: false
+validation_epochs: 50
+validation_prompt: null
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/1724847169.9458585/events.out.tfevents.1724847169.1400ec26ecc4.1380.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94522080cd6159aa1d5ee512a05235454b261738803d59a0548fe2d507ac75f5
+size 3729

logs/dreambooth-lora-sd-xl/1724847169.9638345/hparams.yml

@@ -0,0 +1,79 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+adam_weight_decay_text_encoder: 0.01
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: text
+center_crop: false
+checkpointing_steps: 10000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+clip_skip: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: busetolunay/deneme_building
+do_edm_style_training: false
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: busetolunay/ace2
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: <s0><s1> style
+learning_rate: 1.0
+local_rank: 0
+logging_dir: logs
+lora_unet_blocks: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_steps: 1000
+mixed_precision: bf16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 143
+num_validation_images: 4
+optimizer: prodigy
+output_dir: ace2
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+prior_generation_precision: null
+prior_loss_weight: 1.0
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 64
+repeats: 1
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+snr_gamma: 5.0
+text_encoder_lr: 1.0
+token_abstraction: a0ce
+train_batch_size: 1
+train_text_encoder: false
+train_text_encoder_frac: 1.0
+train_text_encoder_ti: true
+train_text_encoder_ti_frac: 0.5
+use_8bit_adam: false
+use_blora: false
+use_dora: false
+validation_epochs: 50
+validation_prompt: null
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/1724849298.9524682/events.out.tfevents.1724849298.1400ec26ecc4.1757.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d061c33f8e72ae7350cce0d5ec9e992963dd260e1849c852a804cde229999d48
+size 3729

logs/dreambooth-lora-sd-xl/1724849298.9668312/hparams.yml

@@ -0,0 +1,79 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+adam_weight_decay_text_encoder: 0.01
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: text
+center_crop: false
+checkpointing_steps: 10000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+clip_skip: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: busetolunay/deneme_building
+do_edm_style_training: false
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: busetolunay/ace2
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: <s0><s1> style
+learning_rate: 1.0
+local_rank: 0
+logging_dir: logs
+lora_unet_blocks: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_steps: 1000
+mixed_precision: bf16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 143
+num_validation_images: 4
+optimizer: prodigy
+output_dir: ace2
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+prior_generation_precision: null
+prior_loss_weight: 1.0
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 32
+repeats: 1
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+snr_gamma: 5.0
+text_encoder_lr: 1.0
+token_abstraction: a0ce
+train_batch_size: 1
+train_text_encoder: false
+train_text_encoder_frac: 1.0
+train_text_encoder_ti: true
+train_text_encoder_ti_frac: 0.5
+use_8bit_adam: false
+use_blora: false
+use_dora: false
+validation_epochs: 50
+validation_prompt: null
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/events.out.tfevents.1724832769.3273fd9608c9.1994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03be4698f4847b7f04bf47b892d136fa505828be8b89b0aaabf2c7633f4b906
+size 125834

logs/dreambooth-lora-sd-xl/events.out.tfevents.1724847169.1400ec26ecc4.1380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a82cf7896b5d9fe031ea5e35c652bd9f1ae08ce977d7184f752f4a6c642704
+size 83834

logs/dreambooth-lora-sd-xl/events.out.tfevents.1724849298.1400ec26ecc4.1757.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f67747c790d62340acf64b6d17112c1fc4c91e87b1fd2c916327945bd0bbd3
+size 83834

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a918a161aeef1638f5eb096653e417854397be9635ce5cea528aaa41e2a93528
+size 185963768