Upload 122 files

.gitattributes

@@ -33,3 +33,73 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-100.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-100/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-100/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-100/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-200.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-200/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-200/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-200/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-300.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-300/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-300/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-300/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-400.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-400/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-400/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-400/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-500.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-500/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-500/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/10_classes_500_epoch/samples/sample-500/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-100.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-100/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-100/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-100/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-200.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-200/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-200/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-200/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-300.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-300/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-300/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-300/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-400.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-400/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-400/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-400/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-500.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-500/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-500/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/20_classes_500_epoch/samples/sample-500/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-100.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-100/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-100/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-100/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-200.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-200/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-200/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-200/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-300.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-300/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-300/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-300/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-400.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-400/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-400/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-400/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-500.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-500/a[[:space:]]cat[[:space:]]is[[:space:]]sleeping[[:space:]]on[[:space:]]the[[:space:]]sofa.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-500/a[[:space:]]person[[:space:]]is[[:space:]]dancing.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/30_classes_500_epoch/samples/sample-500/an[[:space:]]airplane[[:space:]]in[[:space:]]the[[:space:]]sky.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-100.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-100/a[[:space:]]long[[:space:]]road[[:space:]]with[[:space:]]a[[:space:]]sunset[[:space:]]in[[:space:]]the[[:space:]]background.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-100/a[[:space:]]man[[:space:]]playing[[:space:]]a[[:space:]]guitar.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-100/a[[:space:]]person[[:space:]]is[[:space:]]playing[[:space:]]drums.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-100/a[[:space:]]watermelon.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-200.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-200/a[[:space:]]long[[:space:]]road[[:space:]]with[[:space:]]a[[:space:]]sunset[[:space:]]in[[:space:]]the[[:space:]]background.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-200/a[[:space:]]man[[:space:]]playing[[:space:]]a[[:space:]]guitar.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-200/a[[:space:]]person[[:space:]]is[[:space:]]playing[[:space:]]drums.gif filter=lfs diff=lfs merge=lfs -text
+Tune-A-Video/outputs/40_classes_200_epoch/samples/sample-200/a[[:space:]]watermelon.gif filter=lfs diff=lfs merge=lfs -text

Tune-A-Video/outputs/10_classes_500_epoch/config.yaml

@@ -0,0 +1,46 @@
+pretrained_model_path: /userhome/zhoutianyi/Zhoutianyi/Mutilmodel/huggingface/stable-diffusion-v1-4
+output_dir: ./outputs/10_classes_500_epoch/
+train_data:
+  video_path: /userhome/zhoutianyi/Zhoutianyi/dataset/SEED-DV/output/block1/163.mp4
+  prompt: a turtle swimming in the water
+  n_sample_frames: 6
+  width: 512
+  height: 288
+  sample_start_idx: 0
+  sample_frame_rate: 2
+validation_data:
+  prompts:
+  - a cat is sleeping on the sofa
+  - an airplane in the sky
+  - a person is dancing
+  video_length: 6
+  width: 512
+  height: 288
+  num_inference_steps: 50
+  guidance_scale: 12.5
+  use_inv_latent: false
+  num_inv_steps: 50
+validation_steps: 100
+trainable_modules:
+- attn1.to_q
+- attn2.to_q
+- attn_temp
+train_batch_size: 10
+max_train_steps: 500
+learning_rate: 3.0e-05
+scale_lr: false
+lr_scheduler: constant
+lr_warmup_steps: 0
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_weight_decay: 0.01
+adam_epsilon: 1.0e-08
+max_grad_norm: 1.0
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+checkpointing_steps: 1000
+resume_from_checkpoint: null
+mixed_precision: fp16
+use_8bit_adam: false
+enable_xformers_memory_efficient_attention: true
+seed: 33

Tune-A-Video/outputs/10_classes_500_epoch/model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "TuneAVideoPipeline",
+  "_diffusers_version": "0.11.1",
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    null,
+    "UNet3DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

Tune-A-Video/outputs/10_classes_500_epoch/scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.11.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

Tune-A-Video/outputs/10_classes_500_epoch/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/userhome/zhoutianyi/Zhoutianyi/Mutilmodel/huggingface/stable-diffusion-v1-4",
+  "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": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

Tune-A-Video/outputs/10_classes_500_epoch/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5298945b1f3150e6debdcf55e32cd3c817a8d7efa6ded70b22dd9c1c0c68998f
+size 246188314

Tune-A-Video/outputs/10_classes_500_epoch/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
+  }
+}

Tune-A-Video/outputs/10_classes_500_epoch/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|>"
+}

Tune-A-Video/outputs/10_classes_500_epoch/unet/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.11.1",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "DownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock3DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

Tune-A-Video/outputs/10_classes_500_epoch/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2f1223e8c8a3a0a64cda06b624dbad365452931252e0ff7b2717670d9afb76
+size 371195904

Tune-A-Video/outputs/10_classes_500_epoch/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.11.1",
+  "_name_or_path": "/userhome/zhoutianyi/Zhoutianyi/Mutilmodel/huggingface/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

Tune-A-Video/outputs/10_classes_500_epoch/vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695a1a027d19dfd499c075f2addfd728cdd111cc57e5aa544a99b3a5a445d068
+size 167408066

Tune-A-Video/outputs/20_classes_500_epoch/config.yaml

@@ -0,0 +1,46 @@
+pretrained_model_path: /userhome/zhoutianyi/Zhoutianyi/Mutilmodel/huggingface/stable-diffusion-v1-4
+output_dir: ./outputs/20_classes_500_epoch/
+train_data:
+  video_path: /userhome/zhoutianyi/Zhoutianyi/dataset/SEED-DV/output/block1/163.mp4
+  prompt: a turtle swimming in the water
+  n_sample_frames: 6
+  width: 512
+  height: 288
+  sample_start_idx: 0
+  sample_frame_rate: 2
+validation_data:
+  prompts:
+  - a cat is sleeping on the sofa
+  - an airplane in the sky
+  - a person is dancing
+  video_length: 6
+  width: 512
+  height: 288
+  num_inference_steps: 50
+  guidance_scale: 12.5
+  use_inv_latent: false
+  num_inv_steps: 50
+validation_steps: 100
+trainable_modules:
+- attn1.to_q
+- attn2.to_q
+- attn_temp
+train_batch_size: 10
+max_train_steps: 500
+learning_rate: 3.0e-05
+scale_lr: false
+lr_scheduler: constant
+lr_warmup_steps: 0
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_weight_decay: 0.01
+adam_epsilon: 1.0e-08
+max_grad_norm: 1.0
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+checkpointing_steps: 1000
+resume_from_checkpoint: null
+mixed_precision: fp16
+use_8bit_adam: false
+enable_xformers_memory_efficient_attention: true
+seed: 33

Tune-A-Video/outputs/20_classes_500_epoch/model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "TuneAVideoPipeline",
+  "_diffusers_version": "0.11.1",
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    null,
+    "UNet3DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}