vvonchain commited on
Commit
6b0bcf4
1 Parent(s): 5bfec11

End of training

Browse files
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: openrail++
4
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
5
+ instance_prompt: a photo of sks dog
6
+ tags:
7
+ - stable-diffusion-xl
8
+ - stable-diffusion-xl-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - lora
12
+ inference: true
13
+ ---
14
+
15
+ # LoRA DreamBooth - vvonchain/lora-trained-xl-colab
16
+
17
+ These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
18
+
19
+
20
+
21
+ LoRA for the text encoder was enabled: False.
22
+
23
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
logs/dreambooth-lora-sd-xl/1691701244.2334597/events.out.tfevents.1691701244.f668d567e54a.2128.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc04f823e9f09ddb6e3e24b1ee485d25d3830d6e56ab32f9aebfb303bf9724e
3
+ size 2713
logs/dreambooth-lora-sd-xl/1691701244.235254/hparams.yml ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 717
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_prompt: null
11
+ crops_coords_top_left_h: 0
12
+ crops_coords_top_left_w: 0
13
+ dataloader_num_workers: 0
14
+ enable_xformers_memory_efficient_attention: true
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ instance_data_dir: dog
20
+ instance_prompt: a photo of sks dog
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_num_cycles: 1
25
+ lr_power: 1.0
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_steps: 500
30
+ mixed_precision: fp16
31
+ num_class_images: 100
32
+ num_train_epochs: 250
33
+ num_validation_images: 4
34
+ output_dir: lora-trained-xl-colab
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ rank: 4
41
+ report_to: tensorboard
42
+ resolution: 1024
43
+ resume_from_checkpoint: null
44
+ revision: null
45
+ sample_batch_size: 4
46
+ scale_lr: false
47
+ seed: 0
48
+ train_batch_size: 2
49
+ train_text_encoder: false
50
+ use_8bit_adam: true
51
+ validation_epochs: 50
52
+ validation_prompt: null
53
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1691701244.f668d567e54a.2128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7f9a2dddd09359cea8986104fe4c8aa66fcb55fb07dd414541857e40995a3f
3
+ size 62702
pytorch_lora_weights.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2293445eb9576816c7d51f95ede2badb82d1a831648a750363794c9b7d677b
3
+ size 23664755