upload weights, including cc_projection

cc_projection/config.json

@@ -0,0 +1,4 @@
+{
+  "_class_name": "CCProjection",
+  "_diffusers_version": "0.18.2"
+}

cc_projection/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9065a7f5c466c78ab12ab89f4325ef1e75c17500e77e420cf0648834e55930cc
+size 2375911

feature_extractor/preprocessor_config.json

@@ -14,7 +14,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPFeatureExtractor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2"
+}

image_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c304e9a1c99835f6c2d355cbb5438e7e6204d4903b2f1b056120be4bd5050f1f
+size 1215996977

model_index.json

@@ -1,26 +1,26 @@
 {
-  "_class_name": "StableDiffusionPipeline",
+  "_class_name": "Zero1to3StableDiffusionPipeline",
   "_diffusers_version": "0.18.2",
+  "cc_projection": [
+    "pipeline_zero1to3",
+    "CCProjection"
+  ],
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
   ],
-  "requires_safety_checker": true,
+  "requires_safety_checker": false,
   "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
+    "DDIMScheduler"
   ],
   "unet": [
     "diffusers",

scheduler/scheduler_config.json

@@ -1,15 +1,19 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "DDIMScheduler",
   "_diffusers_version": "0.18.2",
   "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
 }

unet/config.json

@@ -46,7 +46,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 32,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -59,6 +59,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
+  "upcast_attention": null,
   "use_linear_projection": false
 }

vae/config.json

@@ -19,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 256,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",