Upload safetensor

.gitattributes

@@ -33,3 +33,4 @@ 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
+*.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,29 @@
 ---
 license: mit
+tags:
+ - video generation
+ - CreateAI
+pipeline_tag: image-to-video
+library_name: diffusers
 ---
+
+# LayerAnimate-Mix
+
+[Project](https://layeranimate.github.io) | [Github](https://github.com/IamCreateAI/LayerAnimate) | [Paper](https://arxiv.org/abs/2501.08295)
+
+<div align="center"> <img src='demos.gif'></img></div>
+
+**LayerAnimate** is a novel video diffusion framework with layer-aware architecture that empowers the manipulation of layers through layer-level controls.
+
+## Citation
+
+Please consider citing our work as follows if it is helpful.
+
+```bib
+@article{yang2025layeranimate,
+  author    = {Yang, Yuxue and Fan, Lue and Lin, Zuzeng and Wang, Feng and Zhang, Zhaoxiang},
+  title     = {LayerAnimate: Layer-specific Control for Animation},
+  journal   = {arXiv preprint arXiv:2501.08295},
+  year      = {2025},
+}
+```

image_projector/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "Resampler",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "models/i2v",
+  "depth": 4,
+  "dim": 1024,
+  "dim_head": 64,
+  "embedding_dim": 1280,
+  "ff_mult": 4,
+  "heads": 12,
+  "num_queries": 16,
+  "output_dim": 1024,
+  "video_length": 16
+}

image_projector/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893a58eb98b1b2ed33ccd635ebf8ddad825ff20d0959b582964fd03cc8e37e30
+size 97579608

layer_controlnet/config.json

@@ -0,0 +1,49 @@
+{
+  "_class_name": "LayerControlNet",
+  "_diffusers_version": "0.30.2",
+  "addition_attention": true,
+  "attention_resolutions": [
+    4,
+    2,
+    1
+  ],
+  "channel_mult": [
+    1,
+    2,
+    4
+  ],
+  "condition_channels": {
+    "motion_score": 2,
+    "sketch": 4,
+    "trajectory": 3
+  },
+  "context_dim": 1024,
+  "control_injection_mode": "add",
+  "conv_resample": true,
+  "default_fps": 24,
+  "dims": 2,
+  "dropout": 0.1,
+  "fps_condition": true,
+  "ignore_noisy_latents": true,
+  "image_cross_attention": true,
+  "image_cross_attention_scale_learnable": false,
+  "in_channels": 5,
+  "model_channels": 320,
+  "num_head_channels": 64,
+  "num_heads": -1,
+  "num_res_blocks": 2,
+  "out_channels": 4,
+  "resblock_updown": false,
+  "temporal_attention": true,
+  "temporal_conv": true,
+  "temporal_length": 16,
+  "temporal_selfatt_only": true,
+  "tempspatial_aware": false,
+  "transformer_depth": 1,
+  "use_causal_attention": false,
+  "use_checkpoint": true,
+  "use_linear": true,
+  "use_relative_position": false,
+  "use_scale_shift_norm": false,
+  "use_vae_for_trajectory": false
+}

layer_controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370fda8bb902ca1fe3c58811240d608a8b8f6ff22e70efba9c1048d8fe368480
+size 682530392

scheduler/scheduler_config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.30.2",
+  "beta_end": 0.012,
+  "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": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

unet/config.json

@@ -0,0 +1,43 @@
+{
+  "_class_name": "UNetModel",
+  "_diffusers_version": "0.30.2",
+  "addition_attention": true,
+  "attention_resolutions": [
+    4,
+    2,
+    1
+  ],
+  "channel_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "context_dim": 1024,
+  "conv_resample": true,
+  "default_fps": 24,
+  "dims": 2,
+  "dropout": 0.1,
+  "fps_condition": true,
+  "image_cross_attention": true,
+  "image_cross_attention_scale_learnable": false,
+  "in_channels": 8,
+  "masked_layer_fusion": true,
+  "model_channels": 320,
+  "num_head_channels": 64,
+  "num_heads": -1,
+  "num_res_blocks": 2,
+  "out_channels": 4,
+  "resblock_updown": false,
+  "temporal_attention": true,
+  "temporal_conv": true,
+  "temporal_length": 16,
+  "temporal_selfatt_only": true,
+  "tempspatial_aware": false,
+  "transformer_depth": 1,
+  "use_causal_attention": false,
+  "use_checkpoint": true,
+  "use_linear": true,
+  "use_relative_position": false,
+  "use_scale_shift_norm": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7681439cf7fb436df807b8262f06541bfcc056d293ec2e52352bf2c64c973b37
+size 3001024704

vae/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.30.3",
+  "ddconfig": {
+    "attn_resolutions": [],
+    "ch": 128,
+    "ch_mult": [
+      1,
+      2,
+      4,
+      4
+    ],
+    "double_z": true,
+    "dropout": 0.0,
+    "in_channels": 3,
+    "num_res_blocks": 2,
+    "out_ch": 3,
+    "resolution": 256,
+    "z_channels": 4
+  },
+  "embed_dim": 4,
+  "image_key": "image",
+  "input_dim": 4,
+  "use_checkpoint": false
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7053f0e04f33a165d6c20c27727eb7238676ffdc290ca0cb924acdc080b89ae3
+size 334641012

vae_dualref/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "AutoencoderKL_Dualref",
+  "_diffusers_version": "0.11.1",
+  "ddconfig": {
+    "attn_resolutions": [],
+    "ch": 128,
+    "ch_mult": [
+      1,
+      2,
+      4,
+      4
+    ],
+    "double_z": true,
+    "dropout": 0.0,
+    "in_channels": 3,
+    "num_res_blocks": 2,
+    "out_ch": 3,
+    "resolution": 256,
+    "z_channels": 4
+  },
+  "embed_dim": 4,
+  "image_key": "image",
+  "input_dim": 4,
+  "use_checkpoint": false
+}

vae_dualref/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec01046000da70640a5f146bc18e9438181ec3ee9cd27c71ab2da3ca9ea8bdde
+size 399810404