ClaireOzzz commited on
Commit
b254fe6
1 Parent(s): 69d81a5

saving checkpoint-100

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
4
+ instance_prompt: bnwhouse
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - lora
11
+ inference: false
12
+ datasets:
13
+ - ClaireOzzz/BlacknWhiteData
14
+ ---
15
+
16
+ # LoRA DreamBooth - ClaireOzzz/BlacknWhite
17
+ ## MODEL IS CURRENTLY TRAINING ...
18
+ Last checkpoint saved: checkpoint-100
19
+ These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0 trained on @fffiloni's SD-XL trainer.
20
+ The weights were trained on the concept prompt:
21
+ ```
22
+ bnwhouse
23
+ ```
24
+ Use this keyword to trigger your custom model in your prompts.
25
+ LoRA for the text encoder was enabled: False.
26
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
27
+ ## Usage
28
+ Make sure to upgrade diffusers to >= 0.19.0:
29
+ ```
30
+ pip install diffusers --upgrade
31
+ ```
32
+ In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
33
+ ```
34
+ pip install invisible_watermark transformers accelerate safetensors
35
+ ```
36
+ To just use the base model, you can run:
37
+ ```python
38
+ import torch
39
+ from diffusers import DiffusionPipeline, AutoencoderKL
40
+ device = "cuda" if torch.cuda.is_available() else "cpu"
41
+ vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
42
+ pipe = DiffusionPipeline.from_pretrained(
43
+ "stabilityai/stable-diffusion-xl-base-1.0",
44
+ vae=vae, torch_dtype=torch.float16, variant="fp16",
45
+ use_safetensors=True
46
+ )
47
+ pipe.to(device)
48
+ # This is where you load your trained weights
49
+ specific_safetensors = "pytorch_lora_weights.safetensors"
50
+ lora_scale = 0.9
51
+ pipe.load_lora_weights(
52
+ 'ClaireOzzz/BlacknWhite',
53
+ weight_name = specific_safetensors,
54
+ # use_auth_token = True
55
+ )
56
+ prompt = "A majestic bnwhouse jumping from a big stone at night"
57
+ image = pipe(
58
+ prompt=prompt,
59
+ num_inference_steps=50,
60
+ cross_attention_kwargs={"scale": lora_scale}
61
+ ).images[0]
62
+ ```
checkpoint-100/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e97c14de0549e1d6de69870daa67b7ccfeede2e30183b12c7f652f9afd3d3a9
3
+ size 14989511
checkpoint-100/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71cfcc70e1b312552081f1521cc5588d3537560c545c9d05ed614a7c55c13153
3
+ size 23401064
checkpoint-100/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84ce2c2416bf74c353a11ca7a6f83075fde868b9d484c5141af51bc9c125fb7
3
+ size 14599
checkpoint-100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa44e8523f62833816d29aa6c576eaa7783e3bbdb3e132e248b1d8aaee6132b
3
+ size 557
checkpoint-100/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906bdd391189fd16d3160fd1e198eb53687dae580f930cf3f64365609fd5f606
3
+ size 563
logs/dreambooth-lora-sd-xl/1701709622.9888015/events.out.tfevents.1701709622.90593e455941.47048.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6435ec8bab29c4166b56bf2cf62434a8c54910908791f2e2138cdb958c4638bc
3
+ size 2834
logs/dreambooth-lora-sd-xl/1701709622.990543/hparams.yml ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100
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
+ dataset_id: ClaireOzzz/BlacknWhiteData
15
+ enable_xformers_memory_efficient_attention: true
16
+ gradient_accumulation_steps: 2
17
+ gradient_checkpointing: true
18
+ hub_model_id: null
19
+ hub_token: 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
20
+ instance_data_dir: BlacknWhiteData
21
+ instance_prompt: bnwhouse
22
+ learning_rate: 0.0001
23
+ local_rank: -1
24
+ logging_dir: logs
25
+ lr_num_cycles: 1
26
+ lr_power: 1.0
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_steps: 200
31
+ mixed_precision: fp16
32
+ num_class_images: 100
33
+ num_train_epochs: 12
34
+ num_validation_images: 4
35
+ output_dir: BlacknWhite
36
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
37
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
38
+ prior_generation_precision: null
39
+ prior_loss_weight: 1.0
40
+ push_to_hub: true
41
+ rank: 4
42
+ report_to: tensorboard
43
+ resolution: 1024
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ sample_batch_size: 4
47
+ scale_lr: false
48
+ seed: 0
49
+ train_batch_size: 2
50
+ train_text_encoder: false
51
+ use_8bit_adam: true
52
+ validation_epochs: 50
53
+ validation_prompt: null
54
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1701709622.90593e455941.47048.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2624fbdd4ea874d9ea9388594823b8733bb48ecda86a9560f031f01d7eb9502f
3
+ size 15992