PseudoTerminal X
commited on
Trained for 1 epochs and 49000 steps.
Browse filesTrained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', '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 +11 -147
- optimizer.bin +1 -1
- random_states_0.pkl +2 -2
- scheduler.bin +1 -1
- 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.json +1 -1
- transformer/config.json +1 -1
- transformer/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
@@ -47,7 +47,7 @@ You may reuse the base model text encoder for inference.
|
|
47 |
## Training settings
|
48 |
|
49 |
- Training epochs: 1
|
50 |
-
- Training steps:
|
51 |
- Learning rate: 1e-06
|
52 |
- Effective batch size: 192
|
53 |
- Micro-batch size: 24
|
@@ -64,180 +64,44 @@ You may reuse the base model text encoder for inference.
|
|
64 |
|
65 |
### photo-concept-bucket
|
66 |
- Repeats: 0
|
67 |
-
- Total number of images: ~
|
68 |
-
- Total number of aspect buckets:
|
69 |
-
- Resolution: 1.0 megapixels
|
70 |
-
- Cropped: False
|
71 |
-
- Crop style: None
|
72 |
-
- Crop aspect: None
|
73 |
-
### moviecollection
|
74 |
-
- Repeats: 15
|
75 |
-
- Total number of images: ~768
|
76 |
-
- Total number of aspect buckets: 11
|
77 |
-
- Resolution: 1.0 megapixels
|
78 |
-
- Cropped: True
|
79 |
-
- Crop style: random
|
80 |
-
- Crop aspect: random
|
81 |
-
### experimental
|
82 |
-
- Repeats: 0
|
83 |
-
- Total number of images: ~1728
|
84 |
-
- Total number of aspect buckets: 11
|
85 |
- Resolution: 1.0 megapixels
|
86 |
- Cropped: True
|
87 |
- Crop style: random
|
88 |
- Crop aspect: random
|
89 |
-
###
|
90 |
-
- Repeats: 0
|
91 |
-
- Total number of images: ~1152
|
92 |
-
- Total number of aspect buckets: 7
|
93 |
-
- Resolution: 1.0 megapixels
|
94 |
-
- Cropped: True
|
95 |
-
- Crop style: random
|
96 |
-
- Crop aspect: random
|
97 |
-
### sports
|
98 |
- Repeats: 0
|
99 |
-
- Total number of images: ~
|
100 |
- Total number of aspect buckets: 1
|
101 |
- Resolution: 1.0 megapixels
|
102 |
- Cropped: True
|
103 |
- Crop style: random
|
104 |
- Crop aspect: square
|
105 |
-
###
|
106 |
- Repeats: 0
|
107 |
-
- Total number of images: ~
|
108 |
- Total number of aspect buckets: 1
|
109 |
- Resolution: 1.0 megapixels
|
110 |
- Cropped: True
|
111 |
- Crop style: random
|
112 |
- Crop aspect: square
|
113 |
-
###
|
114 |
-
- Repeats: 0
|
115 |
-
- Total number of images: ~14016
|
116 |
-
- Total number of aspect buckets: 3
|
117 |
-
- Resolution: 1.0 megapixels
|
118 |
-
- Cropped: True
|
119 |
-
- Crop style: random
|
120 |
-
- Crop aspect: random
|
121 |
-
### cinemamix-1mp
|
122 |
-
- Repeats: 0
|
123 |
-
- Total number of images: ~7296
|
124 |
-
- Total number of aspect buckets: 3
|
125 |
-
- Resolution: 1.0 megapixels
|
126 |
-
- Cropped: True
|
127 |
-
- Crop style: random
|
128 |
-
- Crop aspect: random
|
129 |
-
### nsfw-1024
|
130 |
-
- Repeats: 0
|
131 |
-
- Total number of images: ~10368
|
132 |
-
- Total number of aspect buckets: 3
|
133 |
-
- Resolution: 1.0 megapixels
|
134 |
-
- Cropped: True
|
135 |
-
- Crop style: random
|
136 |
-
- Crop aspect: random
|
137 |
-
### anatomy
|
138 |
-
- Repeats: 5
|
139 |
-
- Total number of images: ~15168
|
140 |
-
- Total number of aspect buckets: 3
|
141 |
-
- Resolution: 1.0 megapixels
|
142 |
-
- Cropped: True
|
143 |
-
- Crop style: random
|
144 |
-
- Crop aspect: random
|
145 |
-
### bg20k-1024
|
146 |
-
- Repeats: 0
|
147 |
-
- Total number of images: ~89088
|
148 |
-
- Total number of aspect buckets: 3
|
149 |
-
- Resolution: 1.0 megapixels
|
150 |
-
- Cropped: True
|
151 |
-
- Crop style: random
|
152 |
-
- Crop aspect: random
|
153 |
-
### yoga
|
154 |
-
- Repeats: 0
|
155 |
-
- Total number of images: ~2880
|
156 |
-
- Total number of aspect buckets: 3
|
157 |
-
- Resolution: 1.0 megapixels
|
158 |
-
- Cropped: True
|
159 |
-
- Crop style: random
|
160 |
-
- Crop aspect: random
|
161 |
-
### photo-aesthetics
|
162 |
- Repeats: 0
|
163 |
-
- Total number of images: ~
|
164 |
-
- Total number of aspect buckets: 17
|
165 |
-
- Resolution: 1.0 megapixels
|
166 |
-
- Cropped: True
|
167 |
-
- Crop style: random
|
168 |
-
- Crop aspect: random
|
169 |
-
### text-1mp
|
170 |
-
- Repeats: 125
|
171 |
-
- Total number of images: ~12864
|
172 |
-
- Total number of aspect buckets: 3
|
173 |
-
- Resolution: 1.0 megapixels
|
174 |
-
- Cropped: True
|
175 |
-
- Crop style: random
|
176 |
-
- Crop aspect: random
|
177 |
-
### movieposters
|
178 |
-
- Repeats: 10
|
179 |
-
- Total number of images: ~192
|
180 |
- Total number of aspect buckets: 1
|
181 |
- Resolution: 1.0 megapixels
|
182 |
- Cropped: True
|
183 |
- Crop style: random
|
184 |
- Crop aspect: square
|
185 |
-
###
|
186 |
-
- Repeats: 10
|
187 |
-
- Total number of images: ~384
|
188 |
-
- Total number of aspect buckets: 8
|
189 |
-
- Resolution: 1.0 megapixels
|
190 |
-
- Cropped: True
|
191 |
-
- Crop style: random
|
192 |
-
- Crop aspect: random
|
193 |
-
### pixel-art
|
194 |
-
- Repeats: 0
|
195 |
-
- Total number of images: ~384
|
196 |
-
- Total number of aspect buckets: 11
|
197 |
-
- Resolution: 1.0 megapixels
|
198 |
-
- Cropped: True
|
199 |
-
- Crop style: random
|
200 |
-
- Crop aspect: random
|
201 |
-
### signs
|
202 |
- Repeats: 0
|
203 |
-
- Total number of images: ~
|
204 |
- Total number of aspect buckets: 1
|
205 |
- Resolution: 1.0 megapixels
|
206 |
- Cropped: True
|
207 |
- Crop style: random
|
208 |
- Crop aspect: square
|
209 |
-
### midjourney-v6-520k-raw
|
210 |
-
- Repeats: 0
|
211 |
-
- Total number of images: ~513792
|
212 |
-
- Total number of aspect buckets: 58
|
213 |
-
- Resolution: 1.0 megapixels
|
214 |
-
- Cropped: False
|
215 |
-
- Crop style: None
|
216 |
-
- Crop aspect: None
|
217 |
-
### sfwbooru
|
218 |
-
- Repeats: 0
|
219 |
-
- Total number of images: ~271488
|
220 |
-
- Total number of aspect buckets: 73
|
221 |
-
- Resolution: 1.0 megapixels
|
222 |
-
- Cropped: False
|
223 |
-
- Crop style: None
|
224 |
-
- Crop aspect: None
|
225 |
-
### nijijourney-v6-520k-raw
|
226 |
-
- Repeats: 0
|
227 |
-
- Total number of images: ~516288
|
228 |
-
- Total number of aspect buckets: 48
|
229 |
-
- Resolution: 1.0 megapixels
|
230 |
-
- Cropped: False
|
231 |
-
- Crop style: None
|
232 |
-
- Crop aspect: None
|
233 |
-
### dalle3
|
234 |
-
- Repeats: 0
|
235 |
-
- Total number of images: ~1119168
|
236 |
-
- Total number of aspect buckets: 31
|
237 |
-
- Resolution: 1.0 megapixels
|
238 |
-
- Cropped: False
|
239 |
-
- Crop style: None
|
240 |
-
- Crop aspect: None
|
241 |
|
242 |
|
243 |
## Inference
|
|
|
47 |
## Training settings
|
48 |
|
49 |
- Training epochs: 1
|
50 |
+
- Training steps: 49000
|
51 |
- Learning rate: 1e-06
|
52 |
- Effective batch size: 192
|
53 |
- Micro-batch size: 24
|
|
|
64 |
|
65 |
### photo-concept-bucket
|
66 |
- Repeats: 0
|
67 |
+
- Total number of images: ~567360
|
68 |
+
- Total number of aspect buckets: 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
- Resolution: 1.0 megapixels
|
70 |
- Cropped: True
|
71 |
- Crop style: random
|
72 |
- Crop aspect: random
|
73 |
+
### midjourney-v6-520k-raw
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
- Repeats: 0
|
75 |
+
- Total number of images: ~390912
|
76 |
- Total number of aspect buckets: 1
|
77 |
- Resolution: 1.0 megapixels
|
78 |
- Cropped: True
|
79 |
- Crop style: random
|
80 |
- Crop aspect: square
|
81 |
+
### sfwbooru
|
82 |
- Repeats: 0
|
83 |
+
- Total number of images: ~233664
|
84 |
- Total number of aspect buckets: 1
|
85 |
- Resolution: 1.0 megapixels
|
86 |
- Cropped: True
|
87 |
- Crop style: random
|
88 |
- Crop aspect: square
|
89 |
+
### nijijourney-v6-520k-raw
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
90 |
- Repeats: 0
|
91 |
+
- Total number of images: ~416064
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
- Total number of aspect buckets: 1
|
93 |
- Resolution: 1.0 megapixels
|
94 |
- Cropped: True
|
95 |
- Crop style: random
|
96 |
- Crop aspect: square
|
97 |
+
### dalle3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
- Repeats: 0
|
99 |
+
- Total number of images: ~1889680
|
100 |
- Total number of aspect buckets: 1
|
101 |
- Resolution: 1.0 megapixels
|
102 |
- Cropped: True
|
103 |
- Crop style: random
|
104 |
- Crop aspect: square
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
|
106 |
|
107 |
## Inference
|
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 sha256:31436e08edb8a07440cce2917fa89004f961ab7231c1a3661bbc223235e74181
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:642a92b3aa2cf8b8d4ae5f316f2a801766499a1de1c2814d9fb38d3570e395be
|
3 |
+
size 16036
|
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 sha256:24151575a07d0cb2bff32d0adaa4632b4d7035e26a5f5d7418148e7a8289bc63
|
3 |
size 1000
|
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 sha256:021479396c8e26c8703c6d3289b88f6d27f60c50d9378d9f6b233c21ef6eb3e3
|
3 |
+
size 18150691
|
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 sha256:51365d239748bf1c9254199ae86ec71707e258e32f6b502e9462265a4dbe26b2
|
3 |
+
size 4739976
|
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 sha256:51b8582efb189da781d1653f4b91e2e883731dc06c5b574d04473df0c0e55e72
|
3 |
+
size 5409000
|
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 sha256:6e9cbc69396a3a3bbc39cf06195e833c68ecab342f53495c6a8b5b22fa5b2982
|
3 |
+
size 5295188
|
training_state-sfwbooru.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": 49000, "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", "bg20k-1024", "anatomy", "sfwbooru", "nijijourney-v6-520k-raw", "midjourney-v6-520k-raw", "photo-concept-bucket"], "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": 65, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0, "dalle3": 0}}
|
transformer/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "PixArtTransformer2DModel",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
-
"_name_or_path": "/home/ubuntu/training/models/checkpoint-
|
5 |
"activation_fn": "gelu-approximate",
|
6 |
"attention_bias": true,
|
7 |
"attention_head_dim": 72,
|
|
|
1 |
{
|
2 |
"_class_name": "PixArtTransformer2DModel",
|
3 |
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "/home/ubuntu/training/models/checkpoint-48000",
|
5 |
"activation_fn": "gelu-approximate",
|
6 |
"attention_bias": true,
|
7 |
"attention_head_dim": 72,
|
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:cccac28f9d23032a0cfafe5cafb6f80a3ac40496ba900554ac200818f976ae95
|
3 |
size 1816969728
|