Adding `diffusers` weights of this model

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to stabilityai/stable-diffusion-2-1-base

model_index.json

@@ -1,9 +1,9 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.18.0.dev0",
   "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
+    null,
+    null
   ],
   "requires_safety_checker": false,
   "safety_checker": [
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,14 +1,19 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.10.0.dev0",
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.18.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 23,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
-size 1361597018
+oid sha256:1e4aa519f64dc6386f88221a66c106a09fa027b47a20cc0e126687695f2a6669
+size 1361597016

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
-size 1361671895
+oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
+size 1361674657

tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "stabilityai/stable-diffusion-2",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -1,7 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.18.0.dev0",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": [
     5,
     10,
@@ -15,7 +17,12 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -24,22 +31,37 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
   "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": null,
   "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a434f8fdbb51f080ac57a4377281241467c4efc1417b27646ffae989644de60c
-size 3463913445
+oid sha256:3e45229700c1cb952444ecfe5a22126cdfb1ee72a5352ab5d38812b36277d84b
+size 3463925093

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfae3e5f7d459b50f4b0850ead945972c75bb0e1897628933e169eb43974214
-size 3463726498
+oid sha256:f349f136057c7ddefbf454ba56b1f9a84ae15436b9b2e677a6590aa966f1db64
+size 3463726504

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.18.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +19,8 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
-size 334707217
+oid sha256:1b01618945554d9840701d3453d4a9fe3db0db090164a5ed6305641306285b6f
+size 334712113

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
-size 334643276
+oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+size 334643268