End of training 430,000 steps
Browse files- README.md +21 -16
- unet/config.json +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
@@ -24,24 +24,13 @@ This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** with replacem
|
|
24 |
You can use the pipeline like so:
|
25 |
|
26 |
```python
|
27 |
-
from diffusers import
|
28 |
import torch
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
else "cuda"
|
35 |
-
if torch.cuda.is_available()
|
36 |
-
else "cpu"
|
37 |
-
)
|
38 |
-
torch_dtype = torch.float16 if device == "cuda" else torch.float32
|
39 |
-
pipeline = StableDiffusionPipeline.from_pretrained("jangmin/foodai-pipeline-ko", torch_dtype=torch_dtype)
|
40 |
-
pipeline.to(device)
|
41 |
-
|
42 |
-
prompt = "짜장면, 정면에서 본 사진, 그릇에 담긴"
|
43 |
-
image = pipeline(prompt, guidance_scale=8, num_inference_steps=35).images[0]
|
44 |
-
image
|
45 |
```
|
46 |
|
47 |
## Training info
|
@@ -56,3 +45,19 @@ These are the key hyperparameters used during training:
|
|
56 |
* Mixed-precision: bf16
|
57 |
|
58 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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("jangmin/foodai-pipeline-ko", torch_dtype=torch.float16)
|
31 |
+
prompt = "해물 짬뽕"
|
32 |
+
image = pipeline(prompt).images[0]
|
33 |
+
image.save("my_image.png")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
```
|
35 |
|
36 |
## Training info
|
|
|
45 |
* Mixed-precision: bf16
|
46 |
|
47 |
|
48 |
+
|
49 |
+
## Intended uses & limitations
|
50 |
+
|
51 |
+
#### How to use
|
52 |
+
|
53 |
+
```python
|
54 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
55 |
+
```
|
56 |
+
|
57 |
+
#### Limitations and bias
|
58 |
+
|
59 |
+
[TODO: provide examples of latent issues and potential remediations]
|
60 |
+
|
61 |
+
## Training details
|
62 |
+
|
63 |
+
[TODO: describe the data used to train the model]
|
unet/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.29.2",
|
4 |
-
"_name_or_path": "/Jupyter/models/sd-foodai-model-ko/checkpoint-
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.29.2",
|
4 |
+
"_name_or_path": "/Jupyter/models/sd-foodai-model-ko/checkpoint-430000/unet",
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1719125304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aadea00bd97600850c8c26374da0ae20c189a468cfeb6a87e7b9d49ac0373a07
|
3 |
size 1719125304
|