rcannizzaro
commited on
Commit
•
47a22d1
1
Parent(s):
eb501bc
End of training
Browse files- README.md +54 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/vae/config.json +7 -0
- checkpoint-1000/vae/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-850/random_states_0.pkl +3 -0
- checkpoint-850/scaler.pt +3 -0
- checkpoint-850/vae/config.json +7 -0
- checkpoint-850/vae/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-900/random_states_0.pkl +3 -0
- checkpoint-900/scaler.pt +3 -0
- checkpoint-900/vae/config.json +7 -0
- checkpoint-900/vae/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-950/random_states_0.pkl +3 -0
- checkpoint-950/scaler.pt +3 -0
- checkpoint-950/vae/config.json +7 -0
- checkpoint-950/vae/diffusion_pytorch_model.safetensors +3 -0
- config.json +7 -0
- diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
library_name: diffusers
|
4 |
+
tags:
|
5 |
+
- stable-diffusion
|
6 |
+
- stable-diffusion-diffusers
|
7 |
+
- text-to-image
|
8 |
+
- diffusers
|
9 |
+
- diffusers-training
|
10 |
+
base_model: VAE
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
|
18 |
+
# Text-to-image finetuning - rcannizzaro/image_to_one_hot_causal_factor_vae_dsprites
|
19 |
+
|
20 |
+
This Image to One-Hot Causal Factor Encoder/Decoder VAE Network was trained on the **osazuwa/dsprite-counterfactual** dataset. Below are some example images generated with the finetuned pipeline using the following prompts:
|
21 |
+
|
22 |
+
|
23 |
+
|
24 |
+
|
25 |
+
## Training info
|
26 |
+
|
27 |
+
These are the key hyperparameters used during training:
|
28 |
+
|
29 |
+
* Epochs: 7
|
30 |
+
* Learning rate: 0.0001
|
31 |
+
* Batch size: 100
|
32 |
+
* Gradient accumulation steps: 1
|
33 |
+
* Image resolution: 64
|
34 |
+
* Mixed-precision: fp16
|
35 |
+
|
36 |
+
|
37 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://microsoft-research.wandb.io/t-ricardoc/image_to_one_hot_causal_factor_vae_dsprites/runs/ckbzzzmd).
|
38 |
+
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
#### How to use
|
43 |
+
|
44 |
+
```python
|
45 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
46 |
+
```
|
47 |
+
|
48 |
+
#### Limitations and bias
|
49 |
+
|
50 |
+
[TODO: provide examples of latent issues and potential remediations]
|
51 |
+
|
52 |
+
## Training details
|
53 |
+
|
54 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93fc0d8ad918f59cd873db69d49b68dc0e5348ac26581eb40f6492cf5214686e
|
3 |
+
size 14408
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
|
3 |
+
size 988
|
checkpoint-1000/vae/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "VAE",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"aux_loss_multiplier": null,
|
5 |
+
"config_enum": null,
|
6 |
+
"use_cuda": true
|
7 |
+
}
|
checkpoint-1000/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925f208f9324661322b4e7b27d07295b82f73ce998260618de2f9d734576b1d2
|
3 |
+
size 67155340
|
checkpoint-850/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80762d303fe757e7104075b77bd1889b8f2e2d75820afe0488818e5341c303a8
|
3 |
+
size 14408
|
checkpoint-850/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
|
3 |
+
size 988
|
checkpoint-850/vae/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "VAE",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"aux_loss_multiplier": null,
|
5 |
+
"config_enum": null,
|
6 |
+
"use_cuda": true
|
7 |
+
}
|
checkpoint-850/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925f208f9324661322b4e7b27d07295b82f73ce998260618de2f9d734576b1d2
|
3 |
+
size 67155340
|
checkpoint-900/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a54b882e207490a7902bff5c5fa7bd4a771e5a751bef2b71909d4474c2c006
|
3 |
+
size 14408
|
checkpoint-900/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
|
3 |
+
size 988
|
checkpoint-900/vae/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "VAE",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"aux_loss_multiplier": null,
|
5 |
+
"config_enum": null,
|
6 |
+
"use_cuda": true
|
7 |
+
}
|
checkpoint-900/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925f208f9324661322b4e7b27d07295b82f73ce998260618de2f9d734576b1d2
|
3 |
+
size 67155340
|
checkpoint-950/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:492b52b3966ededeba86883614eee78370b7d3e6b0e3f652ec78b22c181d22a9
|
3 |
+
size 14408
|
checkpoint-950/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
|
3 |
+
size 988
|
checkpoint-950/vae/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "VAE",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"aux_loss_multiplier": null,
|
5 |
+
"config_enum": null,
|
6 |
+
"use_cuda": true
|
7 |
+
}
|
checkpoint-950/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925f208f9324661322b4e7b27d07295b82f73ce998260618de2f9d734576b1d2
|
3 |
+
size 67155340
|
config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "VAE",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"aux_loss_multiplier": null,
|
5 |
+
"config_enum": null,
|
6 |
+
"use_cuda": true
|
7 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925f208f9324661322b4e7b27d07295b82f73ce998260618de2f9d734576b1d2
|
3 |
+
size 67155340
|