End of training

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: <s0><s1>
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior
+
+<Gallery />
+
+## Model description
+
+### These are multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
+
+## 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 `TOK` → use `<s0><s1>` in your prompt 
+
+
+
+## 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('multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior', weight_name='pytorch_lora_weights.safetensors')
+embedding_path = hf_hub_download(repo_id='multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior', filename="embeddings.safetensors", repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipe.text_encoder, tokenizer=pipe.tokenizer)
+pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipe.text_encoder_2, tokenizer=pipe.tokenizer_2)
+        
+image = pipeline('<s0><s1>').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)
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- Download the LoRA *.safetensors [here](/multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior/blob/main/pytorch_lora_weights.safetensors). Rename it and place it on your Lora folder.
+- Download the text embeddings *.safetensors [here](/multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior/blob/main/embeddings.safetensors). Rename it and place it on it on your embeddings folder.
+
+All [Files & versions](/multimodalart/polipure-repeats-3-steps-1200-rank64-no-prior/tree/main).
+
+## Details
+
+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.
+

embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bd8c6a03f7c8928d5590062789bf9cf45c479306009790c1670849c2e9e8c1
+size 8344

logs/dreambooth-lora-sd-xl/1702018480.3787982/events.out.tfevents.1702018480.r-multimodalart-autotrain-polipure-repeats-3-steps-12-80bfvbmrg.133.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1e351235d8c1b23eb7cde40aa2dbbe302cc5d561db2a8c9326f07fd98d1aea
+size 3675

logs/dreambooth-lora-sd-xl/1702018480.3807979/hparams.yml

@@ -0,0 +1,74 @@
+adam_beta1: 0.9
+adam_beta2: 0.99
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.0
+allow_tf32: false
+cache_dir: null
+cache_latents: true
+caption_column: prompt
+center_crop: false
+checkpointing_steps: 5000
+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_config_name: null
+dataset_name: ./52d4b5d7-981c-43ff-9e2f-7eea12fba423
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: <s0><s1>
+learning_rate: 1.0
+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: 1200
+mixed_precision: bf16
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 150
+num_validation_images: 4
+optimizer: prodigy
+output_dir: polipure-repeats-3-steps-1200-rank64-no-prior
+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: 0.0
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+rank: 64
+repeats: 3
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 42
+snr_gamma: null
+text_encoder_lr: 1.0
+token_abstraction: TOK
+train_batch_size: 2
+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.1702018480.r-multimodalart-autotrain-polipure-repeats-3-steps-12-80bfvbmrg.133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7eb102feb4454b6c1f8a43f8a07b07eff26a6147b669afd7df692995a792984
+size 100634

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aaa3363d46dfebc8f75121fa6f202827ae464085af4b28688229db0a481443e
+size 371758976