PseudoTerminal X
commited on
Commit
•
920db01
1
Parent(s):
b283c6b
Trained for 0 epochs and 400 steps.
Browse filesTrained with datasets ['text-embeds-sdxl', 'photocb-clip-embeds', 'celebrities', 'movieposters', 'pixel-art', 'moviecollection', 'ethnic', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'photo-concept-bucket']
Learning rate 4e-07, batch size 4, and 4 gradient accumulation steps.
Used DDPM noise scheduler for training with v_prediction prediction type and rescaled_betas_zero_snr=True
Using 'trailing' timestep spacing.
Base model: ptx0/terminus-xl-velocity-v2
VAE: madebyollin/sdxl-vae-fp16-fix
- README.md +3 -3
- optimizer.bin +1 -1
- random_states_0.pkl +2 -2
- scheduler.bin +1 -1
- training_state-anatomy.json +0 -0
- training_state-bg20k-1024.json +2 -2
- training_state-cinemamix-1mp.json +0 -0
- training_state-ethnic.json +0 -0
- training_state-nsfw-1024.json +0 -0
- training_state-photo-aesthetics.json +0 -0
- training_state-photo-concept-bucket.json +2 -2
- training_state-shutterstock.json +0 -0
- training_state-text-1mp.json +0 -0
- training_state-yoga.json +0 -0
- training_state.json +1 -1
- unet/diffusion_pytorch_model-00001-of-00002.safetensors +1 -1
- unet/diffusion_pytorch_model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -44,7 +44,7 @@ You may reuse the base model text encoder for inference.
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 0
|
47 |
-
- Training steps:
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 16
|
50 |
- Micro-batch size: 4
|
@@ -93,7 +93,7 @@ You may reuse the base model text encoder for inference.
|
|
93 |
### ethnic
|
94 |
- Repeats: 0
|
95 |
- Total number of images: 368
|
96 |
-
- Total number of aspect buckets:
|
97 |
- Resolution: 1.0 megapixels
|
98 |
- Cropped: True
|
99 |
- Crop style: random
|
@@ -141,7 +141,7 @@ You may reuse the base model text encoder for inference.
|
|
141 |
### yoga
|
142 |
- Repeats: 0
|
143 |
- Total number of images: 448
|
144 |
-
- Total number of aspect buckets:
|
145 |
- Resolution: 1.0 megapixels
|
146 |
- Cropped: True
|
147 |
- Crop style: random
|
|
|
44 |
## Training settings
|
45 |
|
46 |
- Training epochs: 0
|
47 |
+
- Training steps: 400
|
48 |
- Learning rate: 4e-07
|
49 |
- Effective batch size: 16
|
50 |
- Micro-batch size: 4
|
|
|
93 |
### ethnic
|
94 |
- Repeats: 0
|
95 |
- Total number of images: 368
|
96 |
+
- Total number of aspect buckets: 2
|
97 |
- Resolution: 1.0 megapixels
|
98 |
- Cropped: True
|
99 |
- Crop style: random
|
|
|
141 |
### yoga
|
142 |
- Repeats: 0
|
143 |
- Total number of images: 448
|
144 |
+
- Total number of aspect buckets: 2
|
145 |
- Resolution: 1.0 megapixels
|
146 |
- Cropped: True
|
147 |
- Crop style: random
|
optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15406336826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac95872c7e760c3a7887d3a04ffe8c6e53382dcb8d2b4f1aa5ff98f23c05af08
|
3 |
size 15406336826
|
random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cdfdf650c23a16c6503232590fc07c7e8a3b16496c89270f1f4966bf355e229
|
3 |
+
size 16100
|
scheduler.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edbcb1242ba39fca28d562d47132cef589855d61e3d084ae61a5dfb534259059
|
3 |
size 1000
|
training_state-anatomy.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-bg20k-1024.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff732d37cebe65b88ae3c620c552769c8f32b671b6ab8be8f7e7c69193ea3df5
|
3 |
+
size 1917401
|
training_state-cinemamix-1mp.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-ethnic.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-nsfw-1024.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-photo-aesthetics.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-photo-concept-bucket.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6386307592d1ff9a0d2c984ed24cfc7ff75979c6d5c8ebcd26e1b20f202d0d9
|
3 |
+
size 1915464
|
training_state-shutterstock.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-text-1mp.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-yoga.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"global_step":
|
|
|
1 |
+
{"global_step": 400, "epoch_step": 401, "epoch": 1, "exhausted_backends": ["celebrities", "pixel-art", "movieposters", "moviecollection"], "repeats": {"celebrities": 0, "pixel-art": 0, "movieposters": 0, "moviecollection": 0}}
|
unet/diffusion_pytorch_model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4994180736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96ca08e5a623ca872923ade0185aa2f99fdb6c443dc8e3d9534ca9aa6f8984a
|
3 |
size 4994180736
|
unet/diffusion_pytorch_model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 140970624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:517986623bd50039229e58b00b55933c4f430ea3400970a907ce034f7184302e
|
3 |
size 140970624
|