TejasNavada
commited on
Commit
•
56dee55
1
Parent(s):
5cff022
End of training
Browse files- .gitattributes +1 -0
- README.md +44 -1
- checkpoint-2120/optimizer.bin +3 -0
- checkpoint-2120/pytorch_model.bin +3 -0
- checkpoint-2120/random_states_0.pkl +3 -0
- checkpoint-2120/scaler.pt +3 -0
- checkpoint-2120/scheduler.bin +3 -0
- logs/train_example/events.out.tfevents.1692071459.53481a5e31cf.513.0 +3 -0
- samples/0000.png +3 -0
.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 |
+
samples/0000.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1 +1,44 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: creativeml-openrail-m
|
4 |
+
base_model: runwayml/stable-diffusion-v1-5
|
5 |
+
datasets:
|
6 |
+
- Drozdik/tattoo_v3
|
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 - TejasNavada/tattoo-diffusion
|
16 |
+
|
17 |
+
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **Drozdik/tattoo_v3** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['a dragon on a white background', ' a fiery skull', 'a skull', 'a face', 'a snake and skull']:
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
## Pipeline usage
|
22 |
+
|
23 |
+
You can use the pipeline like so:
|
24 |
+
|
25 |
+
```python
|
26 |
+
from diffusers import DiffusionPipeline
|
27 |
+
import torch
|
28 |
+
|
29 |
+
pipeline = DiffusionPipeline.from_pretrained("TejasNavada/tattoo-diffusion", torch_dtype=torch.float16)
|
30 |
+
prompt = "a dragon on a white background"
|
31 |
+
image = pipeline(prompt).images[0]
|
32 |
+
image.save("my_image.png")
|
33 |
+
```
|
34 |
+
|
35 |
+
## Training info
|
36 |
+
|
37 |
+
These are the key hyperparameters used during training:
|
38 |
+
|
39 |
+
* Epochs: 50
|
40 |
+
* Learning rate: 0.0001
|
41 |
+
* Batch size: 2
|
42 |
+
* Image resolution: 512
|
43 |
+
* Mixed-precision: fp16
|
44 |
+
|
checkpoint-2120/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f536191fc8d789c69245787f3cbc28d45f5d4e9855076c5fc4f9d5e17a1bae5
|
3 |
+
size 1725109957
|
checkpoint-2120/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07e0c24b12467a0e79b58c3b595116dfbe3a1408b0e95ff3b95896c787136f35
|
3 |
+
size 3438369029
|
checkpoint-2120/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8b002b5a92d1bc9c45b5edc244d332a106485ba7e02a63201e17e5989aa7ec
|
3 |
+
size 14663
|
checkpoint-2120/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3257036012d1d9d973faf15eb497c60f2dec03f49d7fac6c8f9fd2a5b9993e9a
|
3 |
+
size 557
|
checkpoint-2120/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90282f1e5c1523b6eb467e7c33e5f6059f2c0f25f6f9527715443f697a608f76
|
3 |
+
size 563
|
logs/train_example/events.out.tfevents.1692071459.53481a5e31cf.513.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8964ebea99244bbc6a973660874f009e839db0533bf3dd568b92be1c72a463ee
|
3 |
+
size 2315933
|
samples/0000.png
ADDED
Git LFS Details
|