Add Diffusers weights

Add Diffusers weights converted from checkpoint `v2-1-0.ckpt` in revision ce66cd87f1360f738348b669b3ecbb79e3c6b8bf

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.11.1",
+  "_diffusers_version": "0.11.0.dev0",
   "feature_extractor": [
     null,
     null

scheduler/scheduler_config.json

@@ -1,12 +1,12 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.11.1",
+  "_diffusers_version": "0.11.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
   "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
+  "prediction_type": "v_prediction",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "_name_or_path": "stabilityai/stable-diffusion-2",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.26.0.dev0",
   "vocab_size": 49408
 }

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

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "name_or_path": "stabilityai/stable-diffusion-2",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.11.1",
+  "_diffusers_version": "0.11.0.dev0",
   "act_fn": "silu",
   "attention_head_dim": [
     5,
@@ -15,7 +15,6 @@
     1280
   ],
   "center_input_sample": false,
-  "class_embed_type": null,
   "cross_attention_dim": 1024,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -30,20 +29,18 @@
   "in_channels": 4,
   "layers_per_block": 2,
   "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,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 96,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
+  "upcast_attention": true,
   "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de981f842c293d09c674830a093379212a6213ccf0e860b811f4885114a8b929
-size 3463913445
+oid sha256:dce504d78cc7f2dc8ee8141cd52cd29ea4589dffe7f6ab72f71717987578e056
+size 3463925093

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.11.1",
+  "_diffusers_version": "0.11.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 768,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9c393b8c32f1f8a280b1ec8b18f835f9325658e68cbf3268c873a19dbc40f4
-size 334707217
+oid sha256:b937b3147b1e4a64d559cee0ee27d5b978c06c18d99bcf5c7417675d627f88b4
+size 334711857