bghira commited on
Commit
a3a8071
·
verified ·
1 Parent(s): f44bb0b

Trained for 1 epochs and 63750 steps.

Browse files

Trained with datasets ['text-embeds', 'sfwbooru-crop']
Learning rate 1.0, batch size 6, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: stabilityai/stable-diffusion-3.5-medium
VAE: None

README.md CHANGED
@@ -329,7 +329,7 @@ You may reuse the base model text encoder for inference.
329
  ## Training settings
330
 
331
  - Training epochs: 1
332
- - Training steps: 63500
333
  - Learning rate: 1.0
334
  - Learning rate schedule: cosine
335
  - Warmup steps: 500000
 
329
  ## Training settings
330
 
331
  - Training epochs: 1
332
+ - Training steps: 63750
333
  - Learning rate: 1.0
334
  - Learning rate schedule: cosine
335
  - Warmup steps: 500000
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f8ef701abe8ff5d7294e0b50943e82c3faa78e05900314d9bec5e4e1fd9453f
3
  size 4493633377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23363f6adabf8db02c2c8c67006664cca9cdcfb728aa83e0bc0e0656febe09f
3
  size 4493633377
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b6bd9fa5f8b116441d8f8877305a374df3047f4ba936b8039fd2b84d2d38240
3
- size 14344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de245d71291b56c16f75bc7bfeb91c5f3f0eaa25e1934adf1aafbad8da972a9e
3
+ size 14408
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c614a9dc16d6c7b8bf00e9e15fc92ab2613bbfc3a808b37a61893792fe7f1fdb
3
  size 1128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08edd92d79fc45bb44f24a50d7f3bfafe50bd394ffdc59aa1433e7f8a194f063
3
  size 1128
training_state-sfwbooru-crop.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b87c091efa83707262ce94058228eb728ad23535fee0bfbf0c4ca49eb5a06ebc
3
- size 15020642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9449e25be2f6ca268bdc91f4b321e29958df1364c9845bbd5f212348ecea4b9
3
+ size 15089642
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 63500, "epoch_step": 63500, "epoch": 2, "exhausted_backends": [], "repeats": {"sfwbooru-crop": 0}}
 
1
+ {"global_step": 63750, "epoch_step": 63750, "epoch": 2, "exhausted_backends": [], "repeats": {"sfwbooru-crop": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db4680a8a8b3da0319e6fbb9fe97b38e5e44c94acb9591094fb1b60a64d06b27
3
  size 4939433672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f292ccdf4024692b534e7e272d1ec3fd44efc8aa4d98fd97d25f40eee4c819
3
  size 4939433672
transformer_ema/config.json CHANGED
@@ -26,7 +26,7 @@
26
  "min_decay": 0.0,
27
  "num_attention_heads": 24,
28
  "num_layers": 24,
29
- "optimization_step": 63500,
30
  "out_channels": 16,
31
  "patch_size": 2,
32
  "pooled_projection_dim": 2048,
 
26
  "min_decay": 0.0,
27
  "num_attention_heads": 24,
28
  "num_layers": 24,
29
+ "optimization_step": 63750,
30
  "out_channels": 16,
31
  "patch_size": 2,
32
  "pooled_projection_dim": 2048,
transformer_ema/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3524ff134c3a25a47a86b019ffe29403e6f3e3262d5f3993b17fb6fcd8f69628
3
  size 9878760864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c826a76a6cdfcd6f77fb62d7e80f8091bc2d93f185d584859b09f8a5c003493f
3
  size 9878760864
transformer_ema/ema_model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c654224d2ac6fb36c31f6d4d81ef43e4b9d28d355c4ef15460c54f23fc8bce2
3
  size 4486612394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d109bb16b001eaed043e910a2e98a1e26a2350ecefffb85f3179a6d555d6b3bc
3
  size 4486612394