Upload 5 files
Browse files
image_encoder/image_encoder_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPVisionModelWithProjection"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"hidden_act": "quick_gelu",
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"image_size": 224,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"model_type": "clip_vision_model",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"patch_size": 14,
|
| 20 |
+
"projection_dim": 768,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.30.2"
|
| 23 |
+
}
|
image_encoder/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c304e9a1c99835f6c2d355cbb5438e7e6204d4903b2f1b056120be4bd5050f1f
|
| 3 |
+
size 1215996977
|
scheduler/scheduler_scheduler_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "DDIMScheduler",
|
| 3 |
+
"_diffusers_version": "0.18.2",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"clip_sample_range": 1.0,
|
| 9 |
+
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
+
"num_train_timesteps": 1000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
+
"rescale_betas_zero_snr": false,
|
| 13 |
+
"sample_max_value": 1.0,
|
| 14 |
+
"set_alpha_to_one": false,
|
| 15 |
+
"steps_offset": 1,
|
| 16 |
+
"thresholding": false,
|
| 17 |
+
"timestep_spacing": "leading",
|
| 18 |
+
"trained_betas": null
|
| 19 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b01618945554d9840701d3453d4a9fe3db0db090164a5ed6305641306285b6f
|
| 3 |
+
size 334712113
|
vae/vae_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.18.2",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
128,
|
| 7 |
+
256,
|
| 8 |
+
512,
|
| 9 |
+
512
|
| 10 |
+
],
|
| 11 |
+
"down_block_types": [
|
| 12 |
+
"DownEncoderBlock2D",
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D"
|
| 16 |
+
],
|
| 17 |
+
"in_channels": 3,
|
| 18 |
+
"latent_channels": 4,
|
| 19 |
+
"layers_per_block": 2,
|
| 20 |
+
"norm_num_groups": 32,
|
| 21 |
+
"out_channels": 3,
|
| 22 |
+
"sample_size": 256,
|
| 23 |
+
"scaling_factor": 0.18215,
|
| 24 |
+
"up_block_types": [
|
| 25 |
+
"UpDecoderBlock2D",
|
| 26 |
+
"UpDecoderBlock2D",
|
| 27 |
+
"UpDecoderBlock2D",
|
| 28 |
+
"UpDecoderBlock2D"
|
| 29 |
+
]
|
| 30 |
+
}
|