Upload folder using huggingface_hub

model_index.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "DiTPipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "transformer": [
+    "sit_transformer_2d",
+    "SiTTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

transformer/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "SiTTransformer2DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 72,
+  "dropout": 0.0,
+  "in_channels": 4,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "norm_type": "ada_norm_zero",
+  "num_attention_heads": 16,
+  "num_embeds_ada_norm": 1000,
+  "num_layers": 28,
+  "out_channels": 8,
+  "patch_size": 2,
+  "sample_size": 32,
+  "upcast_attention": false
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a74c74c67da43135b15e7267610c5d7ee407f3da54e6bcfabe1b1f928f427ae
+size 2999370408

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268