fp8

embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e2591798abd3b934815a2c737b75b1a6555728ca19b68af9ce1d53cc7878d5
+size 74976632

image_encoder/config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 336,
+  "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": "bfloat16",
+  "transformers_version": "4.47.1"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6c30e7c936db6a359515a2222da2d0b7e46e4cf4594541c6e8668b611db664
+size 608635848

image_encoder/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 336,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 336
+}

model_index.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "RuyiInpaintPipeline",
+  "_diffusers_version": "0.29.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.29.0.dev0",
+  "beta_end": 0.03,
+  "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": "v_prediction",
+  "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,
+  "variance_type": "fixed_small"
+}

transformer/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "HunyuanTransformer3DModel",
+  "_diffusers_version": "0.30.2",
+  "activation_fn": "gelu-approximate",
+  "after_norm": false,
+  "attention_head_dim": 176,
+  "basic_block_type": "basic",
+  "cross_attention_dim": 1024,
+  "cross_attention_dim_t5": 2048,
+  "hidden_size": 2816,
+  "in_channels": 48,
+  "learn_sigma": true,
+  "mlp_ratio": 4.3637,
+  "motion_module_kwargs": null,
+  "motion_module_kwargs_even": null,
+  "motion_module_kwargs_odd": null,
+  "motion_module_type": "VanillaGrid",
+  "n_query": 16,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 16,
+  "num_layers": 40,
+  "out_channels": 32,
+  "patch_size": 2,
+  "pooled_projection_dim": 1024,
+  "projection_dim": 1024,
+  "sample_size": 128,
+  "text_len": 77,
+  "text_len_t5": 256,
+  "time_position_encoding": true
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c3c1bc2502a06faa76c5a46c12da5530bb8d1c03a62c9a24e760d3292f2647
+size 7787282152

vae/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.22.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "SpatialDownBlock3D", 
+    "SpatialTemporalDownBlock3D", 
+    "SpatialTemporalDownBlock3D",
+    "SpatialTemporalDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "slice_compression_vae": true,
+  "use_tiling": true,
+  "mid_block_attention_type": "3d",
+  "mini_batch_encoder": 8,
+  "mini_batch_decoder": 2,
+  "up_block_types": [
+    "SpatialUpBlock3D", 
+    "SpatialTemporalUpBlock3D", 
+    "SpatialTemporalUpBlock3D",
+    "SpatialTemporalUpBlock3D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ae604518958d38cbb8f0ba7d0a73c32043380e70bbbaaa18a6552f1ca91df5
+size 492985374