add models

README.md

@@ -0,0 +1,26 @@
+# How to make 
+- pretrained model: [epiCRealism](https://civitai.com/models/25694?modelVersionId=134065) + [hyper CFG lora 12steps](https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SD15-12steps-CFG-lora.safetensors)
+-> merge with lora weight 0.3
+- lora model: [AnimateLCM_sd15_t2v_lora.safetensors](https://huggingface.co/wangfuyun/AnimateLCM/blob/main/AnimateLCM_sd15_t2v_lora.safetensors)-> merge with lora weight 0.3
+
+```python
+# Load the motion adapter
+adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-3", torch_dtype=torch.float16)
+
+# load SD 1.5 based finetuned model
+model_id = "/home/hyejin2/test/models/epiCRealism-hyper-LCM.safetensors"
+
+pipe = AnimateDiffVideoToVideoPipeline.from_single_file(model_id, motion_adapter=adapter, torch_dtype=torch.float16)
+pipe.save_pretrained("models/hello")
+```
+
+# How to use
+```python
+model_id = "jstep750/animatediff_v2v"
+
+pipe = AnimateDiffVideoToVideoPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# enable memory savings
+pipe.enable_vae_slicing()
+pipe.enable_model_cpu_offload()
+```

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AnimateDiffVideoToVideoPipeline",
+  "_diffusers_version": "0.29.2",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "motion_adapter": [
+    "diffusers",
+    "MotionAdapter"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DPMSolverSinglestepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNetMotionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

motion_adapter/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "MotionAdapter",
+  "_diffusers_version": "0.29.2",
+  "_name_or_path": "guoyww/animatediff-motion-adapter-v1-5-3",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "conv_in_channels": null,
+  "motion_layers_per_block": 2,
+  "motion_max_seq_length": 32,
+  "motion_mid_block_layers_per_block": 1,
+  "motion_norm_num_groups": 32,
+  "motion_num_attention_heads": 8,
+  "use_motion_mid_block": false
+}

motion_adapter/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8e6bcf5b5d76d21019aee9f90dccc5276affc0616dc1738431410a64171562
+size 835473448

scheduler/scheduler_config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "DPMSolverSinglestepScheduler",
+  "_diffusers_version": "0.29.2",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.0145,
+  "beta_schedule": "linear",
+  "beta_start": 0.00065,
+  "dynamic_thresholding_ratio": 0.995,
+  "final_sigmas_type": "zero",
+  "lambda_min_clipped": -Infinity,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "solver_order": 2,
+  "solver_type": "midpoint",
+  "thresholding": false,
+  "trained_betas": null,
+  "use_karras_sigmas": true,
+  "variance_type": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c99ab9d59f69f6bd3837ad95469ec4c23e8e87a7d0f07fa23d70a6f173acec3
+size 246144152

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,49 @@
+{
+  "_class_name": "UNetMotionModel",
+  "_diffusers_version": "0.29.2",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlockMotion",
+    "CrossAttnDownBlockMotion",
+    "CrossAttnDownBlockMotion",
+    "DownBlockMotion"
+  ],
+  "downsample_padding": 1,
+  "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_scale_factor": 1,
+  "motion_max_seq_length": 32,
+  "motion_num_attention_heads": 8,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": 8,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlockMotion",
+    "CrossAttnUpBlockMotion",
+    "CrossAttnUpBlockMotion",
+    "CrossAttnUpBlockMotion"
+  ],
+  "use_linear_projection": false,
+  "use_motion_mid_block": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18686171a652fd1c511d0bcaacfe1f124808189fafaff0bcb800d615e27c1b7
+size 2554599720

vae/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.29.2",
+  "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,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "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 sha256:48ac39ebb4b0c7f967336ab7a789fc301f88f9cc298523458ccbd6bb1782af82
+size 167335342