add fp16

safety_checker/config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_commit_hash": null,
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -88,7 +88,7 @@
     "num_attention_heads": 12,
     "num_hidden_layers": 12
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
-size 1216061799
+oid sha256:1d37ca6e57ace94e4c2f03ed0f67b6dc83e1ef1160892074917aa68b28e2afc1
+size 608098599

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.22.0.dev0",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
-size 492305335
+oid sha256:88bd85efb0f84e70521633f578715afb2873db4f2615fdfb1f66e99934715865
+size 246184375

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
+  "name_or_path": "/home/patrick/stable-diffusion-v1-5/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.6.0",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/unet",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7da0e21ba7ea50637bee26e81c220844defdf01aafca02b2c42ecdadb813de4
-size 3438354725
+oid sha256:5019a4fbb455dd9b75192afc3ecf8a8ec875e83812fd51029d2e19277edddebc
+size 1719312805

v1-5-pruned-emaonly.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516
-size 4265380512

v1-inference.yaml

@@ -1,70 +0,0 @@
-model:
-  base_learning_rate: 1.0e-04
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 10000 ]
-        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
-        f_start: [ 1.e-6 ]
-        f_max: [ 1. ]
-        f_min: [ 1. ]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_heads: 8
-        use_spatial_transformer: True
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: True
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.6.0",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
-size 334707217
+oid sha256:51c8904bc921e1e6f354b5fa8e99a1c82ead2f0540114de21557b8abfbb24ad0
+size 167399505