saving checkpoint-5

README.md

@@ -0,0 +1,62 @@
+
+---
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: ppppppps
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- lora
+inference: false
+datasets:
+- ClaireOzzz/OfficialDataset1
+---
+    
+# LoRA DreamBooth - ClaireOzzz/ppppppps
+## MODEL IS CURRENTLY TRAINING ...
+Last checkpoint saved: checkpoint-5
+These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0 trained on @fffiloni's SD-XL trainer. 
+The weights were trained on the concept prompt: 
+```
+ppppppps
+```  
+Use this keyword to trigger your custom model in your prompts. 
+LoRA for the text encoder was enabled: False.
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
+## Usage
+Make sure to upgrade diffusers to >= 0.19.0:
+```
+pip install diffusers --upgrade
+```
+In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
+```
+pip install invisible_watermark transformers accelerate safetensors
+```
+To just use the base model, you can run:
+```python
+import torch
+from diffusers import DiffusionPipeline, AutoencoderKL
+device = "cuda" if torch.cuda.is_available() else "cpu"
+vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
+pipe = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    vae=vae, torch_dtype=torch.float16, variant="fp16",
+    use_safetensors=True
+)
+pipe.to(device)
+# This is where you load your trained weights
+specific_safetensors = "pytorch_lora_weights.safetensors"
+lora_scale = 0.9
+pipe.load_lora_weights(
+    'ClaireOzzz/ppppppps', 
+    weight_name = specific_safetensors,
+    # use_auth_token = True 
+)
+prompt = "A majestic ppppppps jumping from a big stone at night"
+image = pipe(
+    prompt=prompt, 
+    num_inference_steps=50,
+    cross_attention_kwargs={"scale": lora_scale}
+).images[0]
+```

checkpoint-5/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5c3d9fa0d333319d3d78ef7656427c4cdad1c60d531204b32ad3ba0beaae55
+size 14989511

checkpoint-5/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbf1e9718e5f8d8d18a2a9a36a6d897de4f9b1a0a9f515ccb59b3aa6f0ac3cd
+size 23401064

checkpoint-5/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc5eadc9d0f5a0a07514faedc868f7128e44a5a24bd126e2c6df162f13f4ae6
+size 14599

checkpoint-5/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4226304fb62e961f1febc70be2db3d4aa0fa092f6ffb6147df348b679da41079
+size 557

checkpoint-5/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df3bacc250b4ce017e536ba576e645f2d16d19e56f98083d3cbe46791ac548f
+size 563

logs/dreambooth-lora-sd-xl/1712846784.798433/events.out.tfevents.1712846784.3586be902803.23952.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433f17ec20fe2e7a28bea9327ce4e4629d8d57c28e195fa7885c5d1e6b8fb8d0
+size 2800

logs/dreambooth-lora-sd-xl/1712846784.8003275/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
+center_crop: false
+checkpointing_steps: 5
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_id: ClaireOzzz/OfficialDataset1
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: None
+instance_data_dir: OfficialDataset1
+instance_prompt: ppppppps
+learning_rate: 0.0001
+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: 200
+mixed_precision: fp16
+num_class_images: 100
+num_train_epochs: 2
+num_validation_images: 4
+output_dir: ppppppps
+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
+push_to_hub: true
+rank: 4
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+train_batch_size: 2
+train_text_encoder: false
+use_8bit_adam: true
+validation_epochs: 50
+validation_prompt: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/events.out.tfevents.1712846784.3586be902803.23952.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951e4e929f126204b41bdb9ef6e61f75d71ad6c8e9da08d584bb4aa2dbfac625
+size 822