End of training

README.md

@@ -0,0 +1,72 @@
+---
+base_model: black-forest-labs/FLUX.1-dev
+library_name: diffusers
+license: other
+tags:
+- text-to-image
+- diffusers-training
+- diffusers
+- lora
+- flux
+- flux-diffusers
+- template:sd-lora
+instance_prompt: a photo of sks man
+widget: []
+---
+
+<!-- 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. -->
+
+
+# Flux DreamBooth LoRA - markd/trained-flux-lora
+
+<Gallery />
+
+## Model description
+
+These are markd/trained-flux-lora DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev.
+
+The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Flux diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md).
+
+Was LoRA for the text encoder enabled? False.
+
+## Trigger words
+
+You should use `a photo of sks man` to trigger the image generation.
+
+## Download model
+
+[Download the *.safetensors LoRA](markd/trained-flux-lora/tree/main) in the Files & versions tab.
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
+pipeline.load_lora_weights('markd/trained-flux-lora', weight_name='pytorch_lora_weights.safetensors')
+image = pipeline('a photo of sks man').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)
+
+## License
+
+Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
+
+
+## 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-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0c5b5ab0a2f429f3ba90236f6706b6d0b24bbec5ecaddad72c6be41061cfe8
+size 18996742

checkpoint-500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153a299d1d3d7934ca361ee00d014af8adc384c7c6996fd953c13848ac0a0c57
+size 9388696

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a1a9ebb77ed33ab07870e19be152ff45149b284d1050d9ef71af37b78217c4
+size 14344

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d7b85c46d195e3cd6e587d94878d77f315e0a073acfab811251f39fbe891fc
+size 1000

logs/dreambooth-flux-dev-lora/1723548593.1016932/events.out.tfevents.1723548593.827889b4ff72.935.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a620b0e2b4c7c180a8894d019044fd1c121f76a4e3a531ab8fc4fd76568b1a1
+size 3189

logs/dreambooth-flux-dev-lora/1723548593.1348946/hparams.yml

@@ -0,0 +1,70 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.001
+allow_tf32: false
+cache_dir: null
+caption_column: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+guidance_scale: 3.5
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: mark_photos
+instance_prompt: a photo of sks man
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+logit_mean: 0.0
+logit_std: 1.0
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_sequence_length: 512
+max_train_steps: 500
+mixed_precision: bf16
+mode_scale: 1.29
+num_class_images: 100
+num_train_epochs: 125
+num_validation_images: 4
+optimizer: AdamW
+output_dir: trained-flux-lora
+pretrained_model_name_or_path: black-forest-labs/FLUX.1-dev
+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: 4
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+text_encoder_lr: 5.0e-06
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_epochs: 25
+validation_prompt: A photo of sks man
+variant: null
+weighting_scheme: none
+with_prior_preservation: false

logs/dreambooth-flux-dev-lora/1723549313.6672819/events.out.tfevents.1723549313.827889b4ff72.3132.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c891825bcdffadee04c907264afdc85697ba5f836a39d332cf9859e5bb8e274
+size 3207

logs/dreambooth-flux-dev-lora/1723549313.6851246/hparams.yml

@@ -0,0 +1,70 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.001
+allow_tf32: false
+cache_dir: null
+caption_column: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+guidance_scale: 3.5
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: mark_photos
+instance_prompt: a photo of sks man
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+logit_mean: 0.0
+logit_std: 1.0
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_sequence_length: 512
+max_train_steps: 500
+mixed_precision: bf16
+mode_scale: 1.29
+num_class_images: 100
+num_train_epochs: 125
+num_validation_images: 4
+optimizer: AdamW
+output_dir: trained-flux-lora
+pretrained_model_name_or_path: black-forest-labs/FLUX.1-dev
+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: 4
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+text_encoder_lr: 5.0e-06
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_epochs: 25
+validation_prompt: A photo of sks man playing the piano
+variant: null
+weighting_scheme: none
+with_prior_preservation: false

logs/dreambooth-flux-dev-lora/1723549863.7589488/events.out.tfevents.1723549863.827889b4ff72.3365.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b6bbbe08001a528b72b199f8f98194f435a167fa01c452626eee177da73d31
+size 3123

logs/dreambooth-flux-dev-lora/1723549863.7768025/hparams.yml

@@ -0,0 +1,70 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.001
+allow_tf32: false
+cache_dir: null
+caption_column: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+guidance_scale: 3.5
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: mark_photos
+instance_prompt: a photo of sks man
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+logit_mean: 0.0
+logit_std: 1.0
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_sequence_length: 512
+max_train_steps: 500
+mixed_precision: bf16
+mode_scale: 1.29
+num_class_images: 100
+num_train_epochs: 125
+num_validation_images: 4
+optimizer: AdamW
+output_dir: trained-flux-lora
+pretrained_model_name_or_path: black-forest-labs/FLUX.1-dev
+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: 4
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+text_encoder_lr: 5.0e-06
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_epochs: 50
+validation_prompt: null
+variant: null
+weighting_scheme: none
+with_prior_preservation: false

logs/dreambooth-flux-dev-lora/events.out.tfevents.1723548593.827889b4ff72.935.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0ac4c0d2c0c173f97ad02566678b567df5f0cdf8971ddd771426efc82a572e
+size 1306

logs/dreambooth-flux-dev-lora/events.out.tfevents.1723549313.827889b4ff72.3132.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e2c2bdeb1fa1e4c9db0f13944fd7259a002b1e86196685e62841e5224664a8
+size 1306

logs/dreambooth-flux-dev-lora/events.out.tfevents.1723549863.827889b4ff72.3365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f5580ffb123a33a37d430730462208d624e2c0637373896e22898c48528806
+size 156618

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed85642626b9c5927722c33daf93f09242937d743f0c9220c12ef2142dd469a
+size 18727592