huyhuung commited on
Commit
acaaea4
·
verified ·
1 Parent(s): 4367fd2

End of training

Browse files
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion-xl
8
+ - stable-diffusion-xl-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - diffusers-training
12
+ - lora
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # LoRA text2image fine-tuning - huyhuung/irit_SDXL_LoRA
20
+
21
+ These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the None dataset. You can find some example images in the following.
22
+
23
+
24
+
25
+ LoRA for the text encoder was enabled: False.
26
+
27
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
28
+
29
+
30
+ ## Intended uses & limitations
31
+
32
+ #### How to use
33
+
34
+ ```python
35
+ # TODO: add an example code snippet for running this diffusion pipeline
36
+ ```
37
+
38
+ #### Limitations and bias
39
+
40
+ [TODO: provide examples of latent issues and potential remediations]
41
+
42
+ ## Training details
43
+
44
+ [TODO: describe the data used to train the model]
logs/text2image-fine-tune/1746600252.1621418/events.out.tfevents.1746600252.401b96fc3519.311.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba16283b252c87a301de1adee39c7517bc717d21260c9bef7b628d4e17a3026
3
+ size 2588
logs/text2image-fine-tune/1746600252.1641/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: prompt
8
+ center_crop: false
9
+ checkpointing_steps: 717
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irit
14
+ debug_loss: false
15
+ enable_npu_flash_attention: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 3
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ image_interpolation_mode: lanczos
23
+ learning_rate: 0.0001
24
+ local_rank: 0
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 500
31
+ mixed_precision: fp16
32
+ noise_offset: 0
33
+ num_train_epochs: 167
34
+ num_validation_images: 4
35
+ output_dir: irit_SDXL_LoRA
36
+ prediction_type: null
37
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
38
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
39
+ push_to_hub: false
40
+ random_flip: false
41
+ rank: 32
42
+ report_to: tensorboard
43
+ resolution: 1024
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: 0
48
+ snr_gamma: 5.0
49
+ train_batch_size: 1
50
+ train_data_dir: null
51
+ train_text_encoder: true
52
+ use_8bit_adam: true
53
+ validation_epochs: 1
54
+ validation_prompt: null
55
+ variant: null
logs/text2image-fine-tune/1746600393.1643324/events.out.tfevents.1746600393.401b96fc3519.388.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f173f2a177e5a5d4add95644ad9a43b4cd32a034bc6c9c75bc83102d59f8695b
3
+ size 2588
logs/text2image-fine-tune/1746600393.1664574/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: prompt
8
+ center_crop: false
9
+ checkpointing_steps: 717
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irit
14
+ debug_loss: false
15
+ enable_npu_flash_attention: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 3
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ image_interpolation_mode: lanczos
23
+ learning_rate: 0.0001
24
+ local_rank: 0
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 500
31
+ mixed_precision: fp16
32
+ noise_offset: 0
33
+ num_train_epochs: 167
34
+ num_validation_images: 4
35
+ output_dir: irit_SDXL_LoRA
36
+ prediction_type: null
37
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
38
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
39
+ push_to_hub: false
40
+ random_flip: false
41
+ rank: 32
42
+ report_to: tensorboard
43
+ resolution: 1024
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: 0
48
+ snr_gamma: 5.0
49
+ train_batch_size: 1
50
+ train_data_dir: null
51
+ train_text_encoder: false
52
+ use_8bit_adam: true
53
+ validation_epochs: 1
54
+ validation_prompt: null
55
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1746600252.401b96fc3519.311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f600eef3a55e9fc35a2c93c89b2ca919835796694169668614acb18f707a564e
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1746600393.401b96fc3519.388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a80fee9ceef3510fe5a372916d0d07ab021f834606c0eff93a91df2040a344
3
+ size 24461
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0686e0d005c8438a1b56a151ffe353046036524f4fe7f2d9510c858a44b42828
3
+ size 185963768