MaxReynolds commited on
Commit
3fa2808
1 Parent(s): 6cbc9fd

End of training

Browse files
README.md CHANGED
@@ -3,7 +3,7 @@
3
  license: creativeml-openrail-m
4
  base_model: CompVis/stable-diffusion-v1-4
5
  datasets:
6
- - MaxReynolds/Lee_Souder_Combined
7
  tags:
8
  - stable-diffusion
9
  - stable-diffusion-diffusers
@@ -14,7 +14,7 @@ inference: true
14
 
15
  # Text-to-image finetuning - MaxReynolds/MyStreamlitModel
16
 
17
- This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **MaxReynolds/Lee_Souder_Combined** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Rocket Launcher by Lee Souder']:
18
 
19
  ![val_imgs_grid](./val_imgs_grid.png)
20
 
@@ -28,7 +28,7 @@ from diffusers import DiffusionPipeline
28
  import torch
29
 
30
  pipeline = DiffusionPipeline.from_pretrained("MaxReynolds/MyStreamlitModel", torch_dtype=torch.float16)
31
- prompt = "Rocket Launcher by Lee Souder"
32
  image = pipeline(prompt).images[0]
33
  image.save("my_image.png")
34
  ```
@@ -37,7 +37,7 @@ image.save("my_image.png")
37
 
38
  These are the key hyperparameters used during training:
39
 
40
- * Epochs: 40
41
  * Learning rate: 1e-05
42
  * Batch size: 1
43
  * Gradient accumulation steps: 4
@@ -45,4 +45,4 @@ These are the key hyperparameters used during training:
45
  * Mixed-precision: fp16
46
 
47
 
48
- More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/max-f-reynolds/text2image-fine-tune/runs/8u9r6b5p).
 
3
  license: creativeml-openrail-m
4
  base_model: CompVis/stable-diffusion-v1-4
5
  datasets:
6
+ - MaxReynolds/MyPatternDataset
7
  tags:
8
  - stable-diffusion
9
  - stable-diffusion-diffusers
 
14
 
15
  # Text-to-image finetuning - MaxReynolds/MyStreamlitModel
16
 
17
+ This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **MaxReynolds/MyPatternDataset** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['<r4nd0m-l4b3l>']:
18
 
19
  ![val_imgs_grid](./val_imgs_grid.png)
20
 
 
28
  import torch
29
 
30
  pipeline = DiffusionPipeline.from_pretrained("MaxReynolds/MyStreamlitModel", torch_dtype=torch.float16)
31
+ prompt = "<r4nd0m-l4b3l>"
32
  image = pipeline(prompt).images[0]
33
  image.save("my_image.png")
34
  ```
 
37
 
38
  These are the key hyperparameters used during training:
39
 
40
+ * Epochs: 42
41
  * Learning rate: 1e-05
42
  * Batch size: 1
43
  * Gradient accumulation steps: 4
 
45
  * Mixed-precision: fp16
46
 
47
 
48
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/max-f-reynolds/text2image-fine-tune/runs/su62a0vp).
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0ba3a10e9fffcf74c9643b67467eaaceaba444ec9b8177e428beadfc92261e8
3
  size 3438167536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee361f0b0007d7fafd324340dffd8d6222384791ab107aa23a3995e900224f67
3
  size 3438167536
val_imgs_grid.png CHANGED