gaurav-raul commited on
Commit
a61acc1
1 Parent(s): 233119b

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image_2.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-3-medium-diffusers
3
+ library_name: diffusers
4
+ license: openrail++
5
+ tags:
6
+ - text-to-image
7
+ - diffusers-training
8
+ - diffusers
9
+ - lora
10
+ - sd3
11
+ - sd3-diffusers
12
+ - template:sd-lora
13
+ instance_prompt: Toyota Corolla Cross XLE 2022 car
14
+ widget:
15
+ - text: Toyota Corolla Cross XLE 2022 car near beach.
16
+ output:
17
+ url: image_0.png
18
+ - text: Toyota Corolla Cross XLE 2022 car near beach.
19
+ output:
20
+ url: image_1.png
21
+ - text: Toyota Corolla Cross XLE 2022 car near beach.
22
+ output:
23
+ url: image_2.png
24
+ - text: Toyota Corolla Cross XLE 2022 car near beach.
25
+ output:
26
+ url: image_3.png
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+
33
+ # SD3 DreamBooth LoRA - gaurav-raul/corolla-sd3-lora_v3
34
+
35
+ <Gallery />
36
+
37
+ ## Model description
38
+
39
+ These are gaurav-raul/corolla-sd3-lora_v3 DreamBooth LoRA weights for stabilityai/stable-diffusion-3-medium-diffusers.
40
+
41
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [SD3 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md).
42
+
43
+ Was LoRA for the text encoder enabled? False.
44
+
45
+ ## Trigger words
46
+
47
+ You should use `Toyota Corolla Cross XLE 2022 car` to trigger the image generation.
48
+
49
+ ## Download model
50
+
51
+ [Download the *.safetensors LoRA](gaurav-raul/corolla-sd3-lora_v3/tree/main) in the Files & versions tab.
52
+
53
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
54
+
55
+ ```py
56
+ from diffusers import AutoPipelineForText2Image
57
+ import torch
58
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-3-medium-diffusers', torch_dtype=torch.float16).to('cuda')
59
+ pipeline.load_lora_weights('gaurav-raul/corolla-sd3-lora_v3', weight_name='pytorch_lora_weights.safetensors')
60
+ image = pipeline('Toyota Corolla Cross XLE 2022 car near beach.').images[0]
61
+ ```
62
+
63
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
64
+
65
+ - **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/gaurav-raul/corolla-sd3-lora_v3/blob/main/diffusers_lora_weights.safetensors)**.
66
+ - Rename it and place it on your `models/Lora` folder.
67
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:your_new_name:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
68
+
69
+ 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)
70
+
71
+ ## License
72
+
73
+ Please adhere to the licensing terms as described [here](https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE).
74
+
75
+
76
+ ## Intended uses & limitations
77
+
78
+ #### How to use
79
+
80
+ ```python
81
+ # TODO: add an example code snippet for running this diffusion pipeline
82
+ ```
83
+
84
+ #### Limitations and bias
85
+
86
+ [TODO: provide examples of latent issues and potential remediations]
87
+
88
+ ## Training details
89
+
90
+ [TODO: describe the data used to train the model]
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79821e64c291f4232ebb218b56b9dea917cbc34e4e4a25117e65645d525dc492
3
+ size 9598266
checkpoint-1000/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d5e781ea79833fa17e12632f5209b0b3d9a29a4be64a3fb82820e9646321bb6
3
+ size 4742848
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f450d7a61b20252689a0a3fc799e488b09d7ddf742a23e63f67bb976cba2ca13
3
+ size 14540
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c5d10791b798e2e30ced3f57a12d0eb8f21d5f75aa04c4778c06e78d35a611
3
+ size 1000
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41405b71c38210f53aaa1e54e2c65eafe76afd219ff37091d7a9d5c2472a98d8
3
+ size 9598266
checkpoint-1500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1dbd73eb21e16ed7fc969f6f0d436c525237e4c92d21b1a9dfeac02db482c3
3
+ size 4742848
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f620d97fed341a95715b3e5455fa7a8a1978226d3cb868562d9ee7ca214dd7
3
+ size 14540
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
3
+ size 988
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01ea3ebf4b998437485138013a5994c527eee19b1829975f4c0c6ba8dd7f6ec
3
+ size 1000
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5493ebf610cc498b70f24522a7b8d6373a0e73dafd20ecdc9d2928e2e17de096
3
+ size 9598266
checkpoint-2000/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38892cbab34b875a54b4a8d08b3f85b1bdff47a39ba6ef72f397ec7db1a1679b
3
+ size 4742848
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce796e789e6ea020f35d05226710d57799ea370ef67fda0393a3166dfbc81a1
3
+ size 14540
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
3
+ size 988
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907c0bb2e6c59458223ffc0b80f810d0c2648dd620912dcad0519cedd2f16bb9
3
+ size 1000
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34fcfb4971ec81d84163cd351e98273dd7e509302c6cb38ffbc6868e9c8b96dc
3
+ size 9598266
checkpoint-500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67b7d21631db28ce03827d764d4a9b12914c32138c41ad9274f999559183381
3
+ size 4742848
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6828972320efb684467e94945f3019a4306e1b063aa9f164b880015256080f5b
3
+ size 14540
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b34a87aa35045ffe708b610e00ef115943e6886bbf8d5d006e84fcc5958067
3
+ size 1000
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED

Git LFS Details

  • SHA256: d9910a9693d81fc2f8e12d2102dd3cc3ddd5f6babb5d885f5d63491e1c3f1445
  • Pointer size: 132 Bytes
  • Size of remote file: 1.09 MB
image_3.png ADDED
logs/dreambooth-sd3-lora/1720467191.6008027/events.out.tfevents.1720467191.az-aics-03.12086.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79240fcaabcca44de6dc6c177570caaf699a07f2c717d3fd897e7ce89d295eca
3
+ size 3249
logs/dreambooth-sd3-lora/1720467191.6032934/hparams.yml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: false
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ instance_data_dir: /data/sd3_fine_tuning/toyota_corolla_cross_xle_2022
23
+ instance_prompt: Toyota Corolla Cross XLE 2022 car
24
+ learning_rate: 5.0e-06
25
+ local_rank: 0
26
+ logging_dir: logs
27
+ logit_mean: 0.0
28
+ logit_std: 1.0
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: cosine
32
+ lr_warmup_steps: 100
33
+ max_grad_norm: 1.0
34
+ max_sequence_length: 512
35
+ max_train_steps: 2000
36
+ mixed_precision: fp16
37
+ mode_scale: 1.29
38
+ num_class_images: 100
39
+ num_train_epochs: 500
40
+ num_validation_images: 4
41
+ optimizer: AdamW
42
+ output_dir: corolla-sd3-lora_v3
43
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-3-medium-diffusers
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ text_encoder_lr: 5.0e-06
62
+ train_batch_size: 2
63
+ train_text_encoder: false
64
+ use_8bit_adam: false
65
+ validation_epochs: 5
66
+ validation_prompt: Toyota Corolla Cross XLE 2022 car near beach.
67
+ variant: null
68
+ weighting_scheme: logit_normal
69
+ with_prior_preservation: false
logs/dreambooth-sd3-lora/events.out.tfevents.1720467191.az-aics-03.12086.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60fc9e14f8619a4261b6c00c53b8e5142e1c3e38d17e915bdcdbfbdcca4e46f
3
+ size 470590042
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38892cbab34b875a54b4a8d08b3f85b1bdff47a39ba6ef72f397ec7db1a1679b
3
+ size 4742848