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 portrait photo of sks blupus the cat
+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 - strickvl/flux-dreambooth-blupus
+
+<Gallery />
+
+## Model description
+
+These are strickvl/flux-dreambooth-blupus 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 portrait photo of sks blupus the cat` to trigger the image generation.
+
+## Download model
+
+[Download the *.safetensors LoRA](strickvl/flux-dreambooth-blupus/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('strickvl/flux-dreambooth-blupus', weight_name='pytorch_lora_weights.safetensors')
+image = pipeline('A portrait photo of sks blupus the cat').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-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2298f398d96b8dd3a4e69b08ba9e3ff6392204428babb4eff36ff11340ce1feb
+size 149742598

checkpoint-1000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e37138a522e1a7f534c0e5d9c13cc6b95f82f235b1de973d559343af4afb616
+size 74761976

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e892329938b09edf546f7622c81354ab08c78f317665649b7a6cb6bdb4f4f0ef
+size 14604

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d616614e1e01b98e9884f977ff35eabdf257036598f3dd80b10d601a3bca7808
+size 1000

logs/dreambooth-flux-dev-lora/1726136818.7093434/events.out.tfevents.1726136818.dreambooth-pipeline-023466583292643664bc19e97ecfd239-train-mode.60.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4054a41a8f30892490252dc92b7b8b5dbbff2e609973e44ffa741c339c34b499
+size 3149

logs/dreambooth-flux-dev-lora/1726136818.7108507/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: 1000
+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: 1
+gradient_checkpointing: false
+guidance_scale: 3.5
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: /tmp/blupus/
+instance_prompt: A portrait photo of sks blupus the cat
+learning_rate: 0.0002
+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: 1300
+mixed_precision: bf16
+mode_scale: 1.29
+num_class_images: 100
+num_train_epochs: 77
+num_validation_images: 4
+optimizer: AdamW
+output_dir: flux-dreambooth-blupus
+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: 32
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 117
+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.1726136818.dreambooth-pipeline-023466583292643664bc19e97ecfd239-train-mode.60.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bee2769c50d1e93b460823d457b0cba9ab32a1e0aca5e011c77169ad1887808
+size 109034

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8786528ca7d3b01f6599bbbed3e3a369705c9c7121d6cc8dd4ee396e6c26c9
+size 149472944