Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ A Deep Learning project that uses Diffusion transformers (DiT) to generate and T
|
|
15 |
Please see the GitHub repo for more info: https://github.com/ikergarcia1996/AI-Generated-GTAV
|
16 |
|
17 |
|
18 |
-
###
|
19 |
- Trained using 4xNvidia A100 80Gb in Bfloat16
|
20 |
- 64 batch size
|
21 |
- 1e-4 learning rate with constant scheduler and 5% warmup
|
@@ -24,8 +24,8 @@ Please see the GitHub repo for more info: https://github.com/ikergarcia1996/AI-G
|
|
24 |
- ctx noise increased from 0 to 40 during the first 50% of the training. Set to 40 during the remaining steps.
|
25 |
- No Action conditioning
|
26 |
|
27 |
-
###
|
28 |
-
-
|
29 |
- Trained using 4xNvidia A100 80Gb in Bfloat16
|
30 |
- 64 batch size
|
31 |
- 1e-4 learning rate with cosine scheduler to 1e-5 and 5% warmup
|
|
|
15 |
Please see the GitHub repo for more info: https://github.com/ikergarcia1996/AI-Generated-GTAV
|
16 |
|
17 |
|
18 |
+
### dit.safetensors
|
19 |
- Trained using 4xNvidia A100 80Gb in Bfloat16
|
20 |
- 64 batch size
|
21 |
- 1e-4 learning rate with constant scheduler and 5% warmup
|
|
|
24 |
- ctx noise increased from 0 to 40 during the first 50% of the training. Set to 40 during the remaining steps.
|
25 |
- No Action conditioning
|
26 |
|
27 |
+
### dit_action.safetensors
|
28 |
+
- Continue training of `dit.safetensors` with action_conditioning for 210,000 steps.
|
29 |
- Trained using 4xNvidia A100 80Gb in Bfloat16
|
30 |
- 64 batch size
|
31 |
- 1e-4 learning rate with cosine scheduler to 1e-5 and 5% warmup
|