Hugging Face's logo

bghira
/
terminus-xl-velocity-v2

Text-to-Image
Diffusers
Safetensors
stable-diffusion
stable-diffusion-diffusers
full
Model card Files
xet
Community
PseudoTerminal X commited on
Commit
cb0d146
·
verified ·
1 Parent(s): e46323b

Trained for 0 epochs and 4500 steps.

Browse files

Trained with datasets ['text-embeds-sdxl', 'photocb-clip-embeds', 'celebrities', 'movieposters', 'normalnudes', 'propagandaposters', 'guys', 'pixel-art', 'signs', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'sports', 'gay', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'photo-concept-bucket']
Learning rate 4e-07, batch size 8, 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-v1
VAE: madebyollin/sdxl-vae-fp16-fix

Files changed (19) hide show
  1. README.md +4 -4
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +1 -1
  4. scheduler.bin +1 -1
  5. training_state-anatomy.json +2 -2
  6. training_state-architecture.json +2 -2
  7. training_state-bg20k-1024.json +2 -2
  8. training_state-cinemamix-1mp.json +2 -2
  9. training_state-ethnic.json +2 -2
  10. training_state-experimental.json +2 -2
  11. training_state-nsfw-1024.json +2 -2
  12. training_state-photo-aesthetics.json +2 -2
  13. training_state-photo-concept-bucket.json +2 -2
  14. training_state-shutterstock.json +2 -2
  15. training_state-text-1mp.json +2 -2
  16. training_state-yoga.json +2 -2
  17. training_state.json +1 -1
  18. unet/config.json +1 -1
  19. unet/diffusion_pytorch_model.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: 4400
48
  - Learning rate: 4e-07
49
  - Effective batch size: 32
50
  - Micro-batch size: 8
@@ -141,7 +141,7 @@ You may reuse the base model text encoder for inference.
141
  ### experimental
142
  - Repeats: 0
143
  - Total number of images: 3042
144
- - Total number of aspect buckets: 2
145
  - Resolution: 1.0 megapixels
146
  - Cropped: True
147
  - Crop style: random
@@ -149,7 +149,7 @@ You may reuse the base model text encoder for inference.
149
  ### ethnic
150
  - Repeats: 0
151
  - Total number of images: 3076
152
- - Total number of aspect buckets: 3
153
  - Resolution: 1.0 megapixels
154
  - Cropped: True
155
  - Crop style: random
@@ -221,7 +221,7 @@ You may reuse the base model text encoder for inference.
221
  ### yoga
222
  - Repeats: 0
223
  - Total number of images: 3589
224
- - Total number of aspect buckets: 2
225
  - Resolution: 1.0 megapixels
226
  - Cropped: True
227
  - Crop style: random
 
44
  ## Training settings
45
 
46
  - Training epochs: 0
47
+ - Training steps: 4500
48
  - Learning rate: 4e-07
49
  - Effective batch size: 32
50
  - Micro-batch size: 8
 
141
  ### experimental
142
  - Repeats: 0
143
  - Total number of images: 3042
144
+ - Total number of aspect buckets: 3
145
  - Resolution: 1.0 megapixels
146
  - Cropped: True
147
  - Crop style: random
 
149
  ### ethnic
150
  - Repeats: 0
151
  - Total number of images: 3076
152
+ - Total number of aspect buckets: 2
153
  - Resolution: 1.0 megapixels
154
  - Cropped: True
155
  - Crop style: random
 
221
  ### yoga
222
  - Repeats: 0
223
  - Total number of images: 3589
224
+ - Total number of aspect buckets: 3
225
  - Resolution: 1.0 megapixels
226
  - Cropped: True
227
  - Crop style: random
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf3d10323c8e6e944a479c9f4174fbdc5ab367389656339317f62fb9a501c538
3
  size 15406336826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3414a6bb1986b6a0196e9d7268534e029263248b8e47c22846aca6dda7952580
3
  size 15406336826
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c63ea5b391065abae58beb6b85613cce57a683e1b9151ed2f96fa161879f3f5e
3
  size 14344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27f7e9fe5dd76179d72e2e48a2770a37db46cd293c22cdc88250beba1b50e66
3
  size 14344
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d4d3dab79cd28eeb801c15d56dbb5cf73071857b393848397d2521d4a0a8de2
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45208bf3f2442d6774cfd03820db737813b9d5fb8b781378144db873cf39a9db
3
  size 1000
training_state-anatomy.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77aa5a298702e0739501b32ab374be9c40f4210e9df8853ff3b0ffdc80c378e7
3
- size 2559800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b369c3da8134061f0be6fb61ece18735c425ccff86be5ee975477f39f83c9ff9
3
+ size 2585212
training_state-architecture.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64910e55a2400e5cf5341dc33a792d0b44e208b426b45901bd66bffc6bc2419d
3
- size 369233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5871fc3fa67726eb58df92d1507311bcefe4a244df31c7b4bd76dffec23dbd
3
+ size 383044
training_state-bg20k-1024.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:212e3b3c98742e0da8e0c23ac54fbb5050bd5eb66551b538a1b1fec3ae862b60
3
- size 15364690
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e978fc1ffc034ae6499dc9288f5adecf0c1be8f4c736822de20e349a45cb9e54
3
+ size 15415187
training_state-cinemamix-1mp.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:530c40c864610c49b0ac4f2c96ee9ddfb2409bb406c9850dd3520fac0645f118
3
- size 1761620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7187307b79b7263d5c05abbe115cc000ae65c1db06cc5be955c9a44c95433
3
+ size 1796368
training_state-ethnic.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62f4902b456512712751b12f4ade93f50940f80d22630d36a311bdab7fd5f80e
3
- size 1379856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f261562f1db695be9e1139aa953c765632cabd56ef30332b72232262a29fa36
3
+ size 1430478
training_state-experimental.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f69c26a3dc6fd4532cc8391cbd808322abb89421b9366daebc2d44219d343d33
3
- size 701160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f763d5b75caae7f48eb4c510b84eb43dbb5750fb7d622e2aae3ea165f3b7a10c
3
+ size 723734
training_state-nsfw-1024.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b86129b56ddd89ff6c420fb4e38cdf18f576c9624a6ce3f11e0fa8b9d18a5422
3
- size 996635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607c2ddfb331bbaa8e40b6339ab433ba31b4efaaae03fe228eb7694f758e71ab
3
+ size 1010071
training_state-photo-aesthetics.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:676a3fd51d342d90d748b61df48034b1ce1d5774918141d9522ce2f5d9979abd
3
- size 5325684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a332efffb9a515adc1c69117f3e6ae5e49e78b924cde8e1b37bcf1b4405fbe6
3
+ size 5378077
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f989b6554f949ed7820840a165c1448db4ecabb12ab66f74aa6a5f09450f1ee6
3
- size 15294217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbefd12ea9a67f32229d3a8037cfb1ac9e5817855788abccc5f7e0a7889582dd
3
+ size 15305726
training_state-shutterstock.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:020a583f5ef0eac2342f2b16aae41af8f72f34790a06f1500cafcc5afae90fd4
3
- size 5631811
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0e56fca4c401b14c478760154c005b036ccf8b0b16cf0729c7a3bc1e300f23
3
+ size 5707283
training_state-text-1mp.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5f61e8aa1069282e7b03e52ebd10b1ad6841b861275bc36c51e9b9656e48c3a
3
- size 2351776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845940c20c2bb3981cfc1039d426ce39ab3f69769ab4ba05d0e2fb14fa3e8c60
3
+ size 2397936
training_state-yoga.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cdd6800526c8cd51b152ed9870965a736a55c7cc1e256af590abec16787d27a
3
- size 1061309
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31eea1021b82d55824c51bfef0fb261b26f9c86a9fab3e7009cac68cacf588a
3
+ size 1102513
training_state.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a758529c2dc9610e26c1e06dbc7d9682dce3ffe18be1b3beb51f4d6e35fe1814
3
  size 449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42df107d69e772dd7feb0299afd77260e50d80fc162d03284b989cb133c5cce2
3
  size 449
unet/config.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d754e51d0062bdd794c3a5d4d9729db4e2861ae5e662fcfebffddedf82990a7e
3
  size 1837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4f66b29903b7b160884370e09d17b26d1f2fd4bf0193947843628ded13c22c
3
  size 1837
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c4683afeef3f6a9d78a9b365a11c12a9e41bd0105f6cddf135739fc0f3c6e6
3
  size 5135151440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384b8f1b54c1f8dd86acef6a58163fbdf113bb6762844f6e16da203d843babd6
3
  size 5135151440