Hugging Face's logo

RareConcepts
/
pseudo-flex-v2

Text-to-Image
Diffusers
Safetensors
stable-diffusion
stable-diffusion-diffusers
full
Model card Files
xet
Community
PseudoTerminal X commited on
Commit
275528e
·
verified ·
1 Parent(s): 7b3d8b7

Trained for 4 epochs and 48200 steps.

Browse files

Trained with datasets ['text-embeds-sd2x', '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']
Learning rate 4e-07, batch size 4, and 8 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: stabilityai/stable-diffusion-2-1
VAE: None

Files changed (7) hide show
  1. README.md +2 -2
  2. optimizer.bin +1 -1
  3. random_states_0.pkl +2 -2
  4. scheduler.bin +1 -1
  5. training_state-anatomy.json +2 -2
  6. training_state.json +1 -1
  7. 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: 4
47
- - Training steps: 48100
48
  - Learning rate: 4e-07
49
  - Effective batch size: 32
50
  - Micro-batch size: 4
@@ -205,7 +205,7 @@ You may reuse the base model text encoder for inference.
205
  ### anatomy
206
  - Repeats: 5
207
  - Total number of images: 16352
208
- - Total number of aspect buckets: 3
209
  - Resolution: 1.0 megapixels
210
  - Cropped: True
211
  - Crop style: random
 
44
  ## Training settings
45
 
46
  - Training epochs: 4
47
+ - Training steps: 48200
48
  - Learning rate: 4e-07
49
  - Effective batch size: 32
50
  - Micro-batch size: 4
 
205
  ### anatomy
206
  - Repeats: 5
207
  - Total number of images: 16352
208
+ - Total number of aspect buckets: 2
209
  - Resolution: 1.0 megapixels
210
  - Cropped: True
211
  - Crop style: random
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0e0b5e7e3a4b054eea93458c5bf6a886eb9762f4f7f78a44a968ce54566a74
3
  size 5196082660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacfcb85c4d3f6f4ae2569b854c838b72f43ab453f10633e97328c818f3d3531
3
  size 5196082660
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38309691f6faf8b9b41b51a97c6ce6da401b7fd5da0b99b4f0589cff210c75c1
3
- size 14408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d41dba9765913eb1b2e14bc9e10197077c3f0cb913c2db01841874b6febcebb
3
+ size 14344
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb6fffb96dc1f2a3f4fcca7f44c0b0d66917851d03b28ce4bc0273112c3ef7ca
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a4c92505a9551d35530b2c893973142a648dc53d350410ca60efeaa19a041c
3
  size 1000
training_state-anatomy.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc7ebabeb24e50537f970c1dea3109dc95d2daa550b257da75f614c620fa7515
3
- size 3817232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac42dafbc80313595831365aaed423dda0d3ebf4e4b53e4a3bf9555e4f2323e
3
+ size 4261378
training_state.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c8aab492141522c7ca9750de1393cd1d4cec6535c754804976ee14190e7be50
3
  size 708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea28d4422b4bcd44d8279c1a1f52f59129cfb063c6276912fb88573ce31ff0fb
3
  size 708
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4bb790bff4318ea8f0379bcb3d9fca352ce7086c09de7009adf52071dfa99a1
3
  size 1731905416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3055d0eb98a2ddb3587df50f081830300385cb954b7af8b6f88dac5270b8feaf
3
  size 1731905416