Training complete

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: 'a advertising photo of the TOK bottle'
+        
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: a advertising photo of the TOK bottle
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - tushaar21/sdxl_lora_prodigy_1-5_500_rank6
+
+<Gallery />
+
+## Model description
+
+### These are tushaar21/sdxl_lora_prodigy_1-5_500_rank6 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`sdxl_lora_prodigy_1-5_500_rank6.safetensors` here 💾](/tushaar21/sdxl_lora_prodigy_1-5_500_rank6/blob/main/sdxl_lora_prodigy_1-5_500_rank6.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:sdxl_lora_prodigy_1-5_500_rank6:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('tushaar21/sdxl_lora_prodigy_1-5_500_rank6', weight_name='pytorch_lora_weights.safetensors')
+
+image = pipeline('a advertising photo of the TOK bottle').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
+
+You should use a advertising photo of the TOK bottle to trigger the image generation.
+
+## Details
+All [Files & versions](/tushaar21/sdxl_lora_prodigy_1-5_500_rank6/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: False.
+
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
+

logs/dreambooth-lora-sd-xl/1708800042.4663558/events.out.tfevents.1708800042.fc714bb9c916.4961.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a18013f1c815ccaa0cc22b97f30fbd4716b6e164573b59e02d01949bbe8f4a
+size 3615

logs/dreambooth-lora-sd-xl/1708800042.4684882/hparams.yml

@@ -0,0 +1,75 @@
+adam_beta1: 0.9
+adam_beta2: 0.99
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: null
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: prompt
+center_crop: false
+checkpointing_steps: 700
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: /content/drive/MyDrive/training4/
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: a advertising photoshoot of the <s0><s1> on a stylish white background
+  with <s0><s1> flowers around it
+learning_rate: 1.5
+local_rank: -1
+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_steps: 500
+mixed_precision: fp16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 21
+num_validation_images: 4
+optimizer: prodigy
+output_dir: sdxl_lora_prodigy_1-5_500_rank6
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+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: false
+random_flip: false
+rank: 6
+repeats: 2
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+snr_gamma: 5.0
+text_encoder_lr: 1.5
+token_abstraction: TOK
+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
+validation_epochs: 50
+validation_prompt: null
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/1708801254.0127287/events.out.tfevents.1708801254.fc714bb9c916.10527.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3591ff82f88db626a0dbd91abd4c74f65ddf2de6f9cb7cee0b380f8a8161b23c
+size 3615

logs/dreambooth-lora-sd-xl/1708801254.0151246/hparams.yml

@@ -0,0 +1,75 @@
+adam_beta1: 0.9
+adam_beta2: 0.99
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: null
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: prompt
+center_crop: false
+checkpointing_steps: 700
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: /content/drive/MyDrive/training4/
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: a advertising photoshoot of the <s0><s1> on a stylish white background
+  with <s0><s1> flowers around it
+learning_rate: 1.5
+local_rank: -1
+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_steps: 500
+mixed_precision: fp16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 21
+num_validation_images: 4
+optimizer: prodigy
+output_dir: sdxl_lora_prodigy_1-5_500_rank6
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+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: false
+random_flip: false
+rank: 6
+repeats: 2
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+snr_gamma: 5.0
+text_encoder_lr: 1.5
+token_abstraction: TOK
+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
+validation_epochs: 50
+validation_prompt: null
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/events.out.tfevents.1708800042.fc714bb9c916.4961.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff53cd97d760668deffc84bdacfa3794a8eb59f24e7b6a5539a62d0ff2249ff
+size 21724

logs/dreambooth-lora-sd-xl/events.out.tfevents.1708801254.fc714bb9c916.10527.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea63a16ad24734bf81e14d4e81fd0c8845a47701258a468e33571a0cc9f1697
+size 167054

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ba5ebbb37e43976ea38518827bf04c51ddcb2f747bc8fc201e6c57b257960d
+size 35002936

sdxl_lora_prodigy_1-5_500_rank6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5113402d3c4c7a163a1f6a6ec924ee98378d000e7601b1e58d0af10387a0dae1
+size 35085736

sdxl_lora_prodigy_1-5_500_rank6_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e511bde18682551acad34b27e23691c92d6e1496871a4cc0744e779c4d0ca6c
+size 16536