shrikant11 commited on
Commit
0db956f
1 Parent(s): 4882c28

End of training

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: runwayml/stable-diffusion-v1-5
5
+ datasets:
6
+ - lambdalabs/pokemon-blip-captions
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - shrikant11/text_to_img_1
16
+
17
+ This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['How are you']:
18
+
19
+ ![val_imgs_grid](./val_imgs_grid.png)
20
+
21
+
22
+ ## Pipeline usage
23
+
24
+ You can use the pipeline like so:
25
+
26
+ ```python
27
+ from diffusers import DiffusionPipeline
28
+ import torch
29
+
30
+ pipeline = DiffusionPipeline.from_pretrained("shrikant11/text_to_img_1", torch_dtype=torch.float16)
31
+ prompt = "How are you"
32
+ image = pipeline(prompt).images[0]
33
+ image.save("my_image.png")
34
+ ```
35
+
36
+ ## Training info
37
+
38
+ These are the key hyperparameters used during training:
39
+
40
+ * Epochs: 1
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 1
44
+ * Image resolution: 512
45
+ * Mixed-precision: None
46
+
logs/text2image-fine-tune/1704267462.9875765/events.out.tfevents.1704267462.8792eaab1ee6.29101.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8501f292863b55b142e685f8de71829e8d6dafc3f4f459dff6a152d377b6aa91
3
+ size 2215
logs/text2image-fine-tune/1704267462.9893029/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: text
8
+ center_crop: true
9
+ checkpointing_steps: 5
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 6
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-pokemon-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
51
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1704267462.8792eaab1ee6.29101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad4f225e0d7f78883f1fa1cd3a18e59201872cfb8b81163c84c72b68fb3d901
3
+ size 463224
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5d225aeb46ebed774f175585b59d504d7c665e3c6edc67128e4053e04533f3
3
  size 3438167536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030ef58c2770761741d93d7b38cf78ed655f37916882aca6997f2d46a78e74c6
3
  size 3438167536
val_imgs_grid.png ADDED