Adding `diffusers` weights of this model

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

model_index.json

@@ -1,9 +1,9 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.8.0",
+  "_diffusers_version": "0.17.0.dev0",
   "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
+    null,
+    null
   ],
   "requires_safety_checker": false,
   "safety_checker": [
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "DPMSolverMultistepScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,14 +1,22 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.8.0",
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "algorithm_type": "dpmsolver++",
   "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,
+  "lower_order_final": true,
   "num_train_timesteps": 1000,
   "prediction_type": "v_prediction",
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
   "steps_offset": 1,
-  "trained_betas": null
+  "thresholding": false,
+  "trained_betas": null,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
+  "_name_or_path": "stabilityai/stable-diffusion-2",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -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": "4.28.1",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681c555376658c81dc273f2d737a2aeb23ddb6d1d8e5b3a7064636d359a22668
+size 680821096

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:e9c787e9388134c1a25dc69934a51a32a2683b38b8a9b017e1f3a692b8ed6b98
-size 1361679905
+oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
+size 1361674657

text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb11b1da63986aaaaefb5ef2100d34109c024ac640cacd9ed697150c1c57f01
+size 680900852

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": "hf-models/stable-diffusion-v2-768x768/tokenizer",
   "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": "0.17.0.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",
@@ -24,23 +31,35 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
+  "encoder_hid_dim": 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_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": 96,
+  "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"
   ],
-  "use_linear_projection": true,
-  "upcast_attention": true
+  "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 sha256:33898360ff5abe5e3c51667a5a7d2fd41238de486cd797d2f70fbe45e1a1c310
+oid sha256:f60dabe36d854f4952bc3f8a21a769aa132da2135b5cf13c0f75cbe5daa63de1
 size 3463925093

unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9377eed7dfd84a3522929555a575b97110ccd8c4a0e7270ac7d31cad1e28dd
+size 1732107093

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3a4d7978884c5e4ef00b62641b1b544b257be2f6715d984188610ad6475ad2
+size 1731904736

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1238522277c48923ff2751e238f2742c562e45643f3d50cc93d163cb30638b0c
-size 3463726498
+oid sha256:96ebf655f21d1d25caef2b054072e550fd2255cf297ab41ffe89faf8566fb090
+size 3463726504

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.8.0",
-  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
+  "_diffusers_version": "0.17.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -21,6 +20,7 @@
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 768,
+  "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:a4302e1efa25f3a47ceb7536bc335715ad9d1f203e90c2d25507600d74006e89
-size 334715313
+oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
+size 334711857

vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13979094c6566d9aa5936879055457022f34a747eeba12542504853385077c8
+size 167405395

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b011e5a18c53888d51a81aa28223ddec87b450c14dc9650d9c3ebbcd17624e
+size 167335350