PseudoTerminal X
commited on
Commit
•
70ba5e7
1
Parent(s):
0f4027c
Trained for 1 epochs and 30000 steps.
Browse filesTrained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'moviecollection', 'experimental', 'ethnic', 'sports', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'movieposters', 'normalnudes', 'pixel-art', 'signs', 'midjourney-v6-520k-raw', 'sfwbooru', 'nijijourney-v6-520k-raw', 'dalle3']
Learning rate 1e-06, batch size 24, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-large
VAE: madebyollin/sdxl-vae-fp16-fix
- README.md +6 -6
- optimizer.bin +1 -1
- random_states_0.pkl +1 -1
- scheduler.bin +1 -1
- training_state-anatomy.json +0 -0
- training_state-bg20k-1024.json +0 -0
- training_state-dalle3.json +2 -2
- training_state-midjourney-v6-520k-raw.json +2 -2
- training_state-nijijourney-v6-520k-raw.json +2 -2
- training_state-photo-concept-bucket.json +2 -2
- training_state-sfwbooru.json +0 -0
- training_state-text-1mp.json +0 -0
- training_state.json +1 -1
- transformer/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
@@ -62,7 +62,7 @@ You may reuse the base model text encoder for inference.
|
|
62 |
## Training settings
|
63 |
|
64 |
- Training epochs: 1
|
65 |
-
- Training steps:
|
66 |
- Learning rate: 1e-06
|
67 |
- Effective batch size: 192
|
68 |
- Micro-batch size: 24
|
@@ -80,7 +80,7 @@ You may reuse the base model text encoder for inference.
|
|
80 |
### photo-concept-bucket
|
81 |
- Repeats: 0
|
82 |
- Total number of images: ~564672
|
83 |
-
- Total number of aspect buckets:
|
84 |
- Resolution: 1.0 megapixels
|
85 |
- Cropped: False
|
86 |
- Crop style: None
|
@@ -224,7 +224,7 @@ You may reuse the base model text encoder for inference.
|
|
224 |
### midjourney-v6-520k-raw
|
225 |
- Repeats: 0
|
226 |
- Total number of images: ~513792
|
227 |
-
- Total number of aspect buckets:
|
228 |
- Resolution: 1.0 megapixels
|
229 |
- Cropped: False
|
230 |
- Crop style: None
|
@@ -232,7 +232,7 @@ You may reuse the base model text encoder for inference.
|
|
232 |
### sfwbooru
|
233 |
- Repeats: 0
|
234 |
- Total number of images: ~271488
|
235 |
-
- Total number of aspect buckets:
|
236 |
- Resolution: 1.0 megapixels
|
237 |
- Cropped: False
|
238 |
- Crop style: None
|
@@ -240,7 +240,7 @@ You may reuse the base model text encoder for inference.
|
|
240 |
### nijijourney-v6-520k-raw
|
241 |
- Repeats: 0
|
242 |
- Total number of images: ~516288
|
243 |
-
- Total number of aspect buckets:
|
244 |
- Resolution: 1.0 megapixels
|
245 |
- Cropped: False
|
246 |
- Crop style: None
|
@@ -248,7 +248,7 @@ You may reuse the base model text encoder for inference.
|
|
248 |
### dalle3
|
249 |
- Repeats: 0
|
250 |
- Total number of images: ~1119168
|
251 |
-
- Total number of aspect buckets:
|
252 |
- Resolution: 1.0 megapixels
|
253 |
- Cropped: False
|
254 |
- Crop style: None
|
|
|
62 |
## Training settings
|
63 |
|
64 |
- Training epochs: 1
|
65 |
+
- Training steps: 30000
|
66 |
- Learning rate: 1e-06
|
67 |
- Effective batch size: 192
|
68 |
- Micro-batch size: 24
|
|
|
80 |
### photo-concept-bucket
|
81 |
- Repeats: 0
|
82 |
- Total number of images: ~564672
|
83 |
+
- Total number of aspect buckets: 10
|
84 |
- Resolution: 1.0 megapixels
|
85 |
- Cropped: False
|
86 |
- Crop style: None
|
|
|
224 |
### midjourney-v6-520k-raw
|
225 |
- Repeats: 0
|
226 |
- Total number of images: ~513792
|
227 |
+
- Total number of aspect buckets: 12
|
228 |
- Resolution: 1.0 megapixels
|
229 |
- Cropped: False
|
230 |
- Crop style: None
|
|
|
232 |
### sfwbooru
|
233 |
- Repeats: 0
|
234 |
- Total number of images: ~271488
|
235 |
+
- Total number of aspect buckets: 24
|
236 |
- Resolution: 1.0 megapixels
|
237 |
- Cropped: False
|
238 |
- Crop style: None
|
|
|
240 |
### nijijourney-v6-520k-raw
|
241 |
- Repeats: 0
|
242 |
- Total number of images: ~516288
|
243 |
+
- Total number of aspect buckets: 9
|
244 |
- Resolution: 1.0 megapixels
|
245 |
- Cropped: False
|
246 |
- Crop style: None
|
|
|
248 |
### dalle3
|
249 |
- Repeats: 0
|
250 |
- Total number of images: ~1119168
|
251 |
+
- Total number of aspect buckets: 2
|
252 |
- Resolution: 1.0 megapixels
|
253 |
- Cropped: False
|
254 |
- Crop style: None
|
optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5451415117
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c5c3524172c5c7fdc86997bff9691007c354427e86a0fb6f21ac27156d3c7c0
|
3 |
size 5451415117
|
random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16100
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7465fd065b49dd9616b627da943c04583757ac9db86da61e68736c4e9921d2
|
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:f99930a90f196bd6f4e7e8666e4021fe8eb7bc320303852641ddb77d29e24739
|
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
The diff for this file is too large to render.
See raw diff
|
|
training_state-dalle3.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 sha256:5a4d148e6371f4ccac84b02848b7bc90fc9b7c8ca4a032c1a172ef4ccbb8f4ce
|
3 |
+
size 9189686
|
training_state-midjourney-v6-520k-raw.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 sha256:763440b8d650fd9a6706c21b9222b91f9140b53fdd78ae43fac5ad1904af6e55
|
3 |
+
size 6784671
|
training_state-nijijourney-v6-520k-raw.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 sha256:165d3127ae2f24e4dc30c7c829b623ebd9e5ef067af45b706a6750df0ae572eb
|
3 |
+
size 7269811
|
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:f4b0eb763811d8bbf45bed1944acf6bea69884b0e3aecccfa4fe1daca2d2636c
|
3 |
+
size 5688858
|
training_state-sfwbooru.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.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"global_step":
|
|
|
1 |
+
{"global_step": 30000, "epoch_step": 1, "epoch": 2, "exhausted_backends": ["pixel-art", "signs", "sports", "ethnic", "experimental", "movieposters", "normalnudes", "yoga", "cinemamix-1mp", "architecture", "moviecollection", "shutterstock", "nsfw-1024", "photo-aesthetics"], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 3, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 1, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
|
transformer/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1816969728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32fb7ec01f6eb0b8e757796720ba5206c9deae585f3b699d73a98028c811f1bc
|
3 |
size 1816969728
|