converted using stablediffusionapi.com

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.17.1",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"

scheduler/scheduler_config.json

@@ -1,15 +1,20 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.17.1",
   "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

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],

unet/config.json

@@ -1,10 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.17.1",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -38,7 +37,6 @@
   "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,
@@ -52,7 +50,6 @@
   "time_embedding_dim": null,
   "time_embedding_type": "positional",
   "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.17.1",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -14,7 +14,6 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
-  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,