Upload 13 files

model_index.json

@@ -6,5 +6,10 @@
   "guidance_scale": null,
   "lift": null,
   "num_inference_steps": null,
-  "seed": null
+  "scheduler": "EulerDiscreteScheduler",
+  "seed": null,
+  "text_encoder": "CLIPTextModel",
+  "tokenizer": "CLIPTokenizer",
+  "unet": "UNet2DConditionModel",
+  "vae": "AutoencoderKL"
 }

pipeline.py

@@ -9,13 +9,13 @@ from diffusers.configuration_utils import ConfigMixin
 class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
     """SuperDiffPipeline."""
 
-    def __init__(self, model: Callable, vae: Callable, text_encoder: Callable, scheduler: Callable, tokenizer: Callable, **kwargs) -> None:
+    def __init__(self, unet: Callable, vae: Callable, text_encoder: Callable, scheduler: Callable, tokenizer: Callable, **kwargs) -> None:
         """__init__.
 
         Parameters
         ----------
-        model : Callable
-            model
+        unet : Callable
+            unet
         vae : Callable
             vae
         text_encoder : Callable
@@ -33,7 +33,7 @@ class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
 
         """
         super().__init__()
-        self.model = model
+        self.unet = unet
         self.vae = vae
         self.text_encoder = text_encoder
         self.tokenizer = tokenizer
@@ -42,7 +42,7 @@ class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
         device = "cuda" if torch.cuda.is_available() else "cpu" 
 
         self.vae.to(device)
-        self.model.to(device)
+        self.unet.to(device)
         self.text_encoder.to(device)
 
         self.register_to_config(
@@ -124,7 +124,7 @@ class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
         embeddings : Callable
             embeddings
         """
-        def v(_x, _e): return self.model(
+        def v(_x, _e): return self.unet(
             _x / ((sigma**2 + 1) ** 0.5), t, encoder_hidden_states=_e
         ).sample
         embeds = torch.cat(embeddings)
@@ -191,7 +191,7 @@ class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
             self.seed
         )  # Seed generator to create the initial latent noise
         latents = torch.randn(
-            (batch_size, self.model.config.in_channels, height // 8, width // 8),
+            (batch_size, self.unet.config.in_channels, height // 8, width // 8),
             generator=generator,
             device=self.device,
         )

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "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",
+  "reverse_transformer_layers_per_block": null,
+  "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,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54d1800033f872c2ede03a45de06d176a53146e43bc9bdb81b0429560a07dc9
+size 3438167536