Hugging Face's logo

gattaplayer
/
besch-style-st-sd35m-lokr-8e-5-bs6-v03

Text-to-Image
Diffusers
sd3
sd3-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
lycoris
Model card Files Community
gattaplayer commited on
Commit
115565e
·
verified ·
1 Parent(s): 34869e3

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -105,7 +105,7 @@ You may reuse the base model text encoder for inference.
105
  ## Training settings
106
 
107
  - Training epochs: 8
108
- - Training steps: 7182
109
  - Learning rate: 8e-05
110
  - Learning rate schedule: polynomial
111
  - Warmup steps: 798
@@ -170,7 +170,7 @@ You may reuse the base model text encoder for inference.
170
  ### BESCH-CROP-SD35M-V03-1024
171
  - Repeats: 1
172
  - Total number of images: 101
173
- - Total number of aspect buckets: 3
174
  - Resolution: 1.048576 megapixels
175
  - Cropped: True
176
  - Crop style: random
@@ -179,7 +179,7 @@ You may reuse the base model text encoder for inference.
179
  ### BESCH-MIX-SD35M-V03-512
180
  - Repeats: 3
181
  - Total number of images: 202
182
- - Total number of aspect buckets: 6
183
  - Resolution: 0.262144 megapixels
184
  - Cropped: True
185
  - Crop style: random
@@ -188,7 +188,7 @@ You may reuse the base model text encoder for inference.
188
  ### BESCH-MIX-SD35M-V03-768
189
  - Repeats: 3
190
  - Total number of images: 202
191
- - Total number of aspect buckets: 13
192
  - Resolution: 0.589824 megapixels
193
  - Cropped: True
194
  - Crop style: random
@@ -206,7 +206,7 @@ You may reuse the base model text encoder for inference.
206
  ### BESCH-MIX-SD35M-V03-1280
207
  - Repeats: 3
208
  - Total number of images: 199
209
- - Total number of aspect buckets: 14
210
  - Resolution: 1.6384 megapixels
211
  - Cropped: True
212
  - Crop style: random
@@ -224,7 +224,7 @@ You may reuse the base model text encoder for inference.
224
  ### BESCH-ORIGINAL-SD35M-V03-768
225
  - Repeats: 3
226
  - Total number of images: 68
227
- - Total number of aspect buckets: 2
228
  - Resolution: 0.589824 megapixels
229
  - Cropped: True
230
  - Crop style: random
@@ -233,7 +233,7 @@ You may reuse the base model text encoder for inference.
233
  ### BESCH-ORIGINAL-SD35M-V03-1024
234
  - Repeats: 3
235
  - Total number of images: 68
236
- - Total number of aspect buckets: 4
237
  - Resolution: 1.048576 megapixels
238
  - Cropped: True
239
  - Crop style: random
 
105
  ## Training settings
106
 
107
  - Training epochs: 8
108
+ - Training steps: 7980
109
  - Learning rate: 8e-05
110
  - Learning rate schedule: polynomial
111
  - Warmup steps: 798
 
170
  ### BESCH-CROP-SD35M-V03-1024
171
  - Repeats: 1
172
  - Total number of images: 101
173
+ - Total number of aspect buckets: 1
174
  - Resolution: 1.048576 megapixels
175
  - Cropped: True
176
  - Crop style: random
 
179
  ### BESCH-MIX-SD35M-V03-512
180
  - Repeats: 3
181
  - Total number of images: 202
182
+ - Total number of aspect buckets: 8
183
  - Resolution: 0.262144 megapixels
184
  - Cropped: True
185
  - Crop style: random
 
188
  ### BESCH-MIX-SD35M-V03-768
189
  - Repeats: 3
190
  - Total number of images: 202
191
+ - Total number of aspect buckets: 2
192
  - Resolution: 0.589824 megapixels
193
  - Cropped: True
194
  - Crop style: random
 
206
  ### BESCH-MIX-SD35M-V03-1280
207
  - Repeats: 3
208
  - Total number of images: 199
209
+ - Total number of aspect buckets: 2
210
  - Resolution: 1.6384 megapixels
211
  - Cropped: True
212
  - Crop style: random
 
224
  ### BESCH-ORIGINAL-SD35M-V03-768
225
  - Repeats: 3
226
  - Total number of images: 68
227
+ - Total number of aspect buckets: 1
228
  - Resolution: 0.589824 megapixels
229
  - Cropped: True
230
  - Crop style: random
 
233
  ### BESCH-ORIGINAL-SD35M-V03-1024
234
  - Repeats: 3
235
  - Total number of images: 68
236
+ - Total number of aspect buckets: 1
237
  - Resolution: 1.048576 megapixels
238
  - Cropped: True
239
  - Crop style: random