Upload 9 files

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "CogVideoXPipeline",
+  "_diffusers_version": "0.31.0",
+  "scheduler": [
+    "diffusers",
+    "CogVideoXDDIMScheduler"
+  ],
+  "text_encoder": [
+    null,
+    null
+  ],
+  "tokenizer": [
+    null,
+    null
+  ],
+  "transformer": [
+    "custom_cogvideox_transformer_3d",
+    "CogVideoXTransformer3DModel"
+  ],
+  "vae": [
+    null,
+    null
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

transformer_T2V/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.31.0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 96,
+  "sample_width": 170,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

transformer_T2V/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b2fc9286adfe838c16f7dff83d0952484606731f1c52e2bf4d9f13a8760587
+size 4977695424

transformer_T2V/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb0e8acfdbcd482cabc8fba4dc2789f517430d7104ff693fd1d54da75973522
+size 4948039832

transformer_T2V/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

vae/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "AutoencoderKLCogVideoX",
+  "_diffusers_version": "0.31.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_height": 480,
+  "sample_width": 720,
+  "scaling_factor": 0.7,
+  "shift_factor": null,
+  "temporal_compression_ratio": 4,
+  "up_block_types": [
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd47d57ad948ff80da0af0cb2e4dcdef65073aba59bccfd383ada9a7d1c02024
+size 431221142