Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task filter=lfs diff=lfs merge=lfs -text
+models/checkpoints/memo/misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task filter=lfs diff=lfs merge=lfs -text

models/checkpoints/2.5D_V1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c373fc73809d546d72a6b640c864857b5c5ed91be6fa892afa88e66249e384
+size 2132625910

models/checkpoints/3Guofeng3_v34.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83e25fe5b70bad595fe4dd6733ee35f0e3ddf8ed4041ab360f9573556e8b3e6
+size 2299933688

models/checkpoints/RealisticModel_v2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa0bb415a08b4f480ad41659eafa8062cafd3857424571200d9c74cb8be7b86
+size 2132621438

models/checkpoints/SUPIR-v0Q_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eef33ec7633122ca23b1e5ef167faa048b5a0845768694d5e8070138ac013ce
+size 2664858464

models/checkpoints/absolutereality_v181.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463d6a9fe8a4b56a4d69ef3692074c0617428dfd8e8f12f9efe3b1e9a71717ce
+size 2132625432

models/checkpoints/animerge_v27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd98dd2fe195654f9e17231c42ae96f1431c1f73bc8193601991bb3c2ce021e9
+size 2132626814

models/checkpoints/anyloraCheckpoint_bakedvaeBlessedFp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef49fbb25fa908bb54ded95abf81ef4b0e21fa0a8de56c40c3d62e768ef7e49a
+size 3455824250

models/checkpoints/ayu_realistic.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7308c649f34a7020dfda590834c92424616d4ed104b7dda414b6f01aace2bd
+size 2498580732

models/checkpoints/cardosAnime_v20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bd0c547c0ffbbcff680a601264ab9003dece7c9afe5ee7746f3b195cdfb78e
+size 4265096689

models/checkpoints/cuteyukimixAdorable_kemiaomiao.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35dae95c7495f1a28d4d1f916d7276db9ed622cf9364acb40d1a8f042460c01c
+size 2378779158

models/checkpoints/cyberrealistic_classicV31.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a722bd93f40adc093b5d2fdb2aa86710285a4a1960122a181416c6be417464fd
+size 2132651162

models/checkpoints/darkSushiMixMix_225D.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca17b08da3254aa2f0242a84ab8641c89d1bc71cc1046fc79f8e906581a97ba
+size 2132627182

models/checkpoints/disneyPixarCartoon_v10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6548414b4947186d0573d1a9f151fa1f1ca0e7c5fbe9e626a5e6f5532f7e654
+size 4244098204

models/checkpoints/dreamshaper_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd
+size 2132625894

models/checkpoints/epicdream_lullaby.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546fb83e40600d143589890e96fbd10191ccf2b7b1ba4af712a43ea24b77c3b1
+size 2132625790

models/checkpoints/flat2DAnimerge_v30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd56bfa12e9ea2f1f3e86a04d0d2cde06a58f2cdf3bfc46cbff6aaa8f00921d
+size 2132626072

models/checkpoints/juggernautXL_v9Rdphoto2Lightning.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8df560d2992ac04299412be6a36fa53a4e7a1b74f27b94867ad3f84f4b425a5
+size 7105348284

models/checkpoints/juggernaut_aftermath.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed60a2f5842de8e6755965ffbf2a0ee273429939f307233c22f7dffd8d7ae3d
+size 5672794804

models/checkpoints/kantanmixSD15_v10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c46570180b4defbf0841cfe4f491f5eaa38f48a61f85f29cf83fdf0dd82ddf
+size 2132626758

models/checkpoints/ltx-video-2b-v0.9.1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23200896c5eddf215c7cb9517820c5763a2b054eb62ba86cbce6b871a4577e3
+size 5716863844

models/checkpoints/ltx-video-2b-v0.9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63111264103e4bb8e7f5f7a653e9417d83c84759a48a945f9fabf7f7ea0d9984
+size 9370440316

models/checkpoints/majicmixRealistic_v7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c819b6d13663ed720c2254f4fe18373107dfef2448d337913c8fc545640881e
+size 2132625894

models/checkpoints/manmaruMix_v30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d34a470c17d0361f2eaf06b555d616b358543be0d019984ad3d65be6b161cc5
+size 2299958656

models/checkpoints/maturemalemix_v14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5b5d7b9cd029dc12fde669209fdb2446e318c17f019b8e381a37e9743ec7aa
+size 2400040472

models/checkpoints/meinamix_meinaV11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ef3e3610eee7f0f6c9f9b82eee26aa404598512d800494d1db344e3bc560b1
+size 2132651818

models/checkpoints/memo/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task filter=lfs diff=lfs merge=lfs -text

models/checkpoints/memo/README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+---
+
+# MEMO
+
+**MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation**
+<br>
+[Longtao Zheng](https://ltzheng.github.io)\*,
+[Yifan Zhang](https://scholar.google.com/citations?user=zuYIUJEAAAAJ)\*,
+[Hanzhong Guo](https://scholar.google.com/citations?user=q3x6KsgAAAAJ)\,
+[Jiachun Pan](https://scholar.google.com/citations?user=nrOvfb4AAAAJ),
+[Zhenxiong Tan](https://scholar.google.com/citations?user=HP9Be6UAAAAJ),
+[Jiahao Lu](https://scholar.google.com/citations?user=h7rbA-sAAAAJ),
+[Chuanxin Tang](https://scholar.google.com/citations?user=3ZC8B7MAAAAJ),
+[Bo An](https://personal.ntu.edu.sg/boan/index.html),
+[Shuicheng Yan](https://scholar.google.com/citations?user=DNuiPHwAAAAJ)
+<br>
+_[Project Page](https://memoavatar.github.io) | [arXiv](https://arxiv.org/abs/2412.04448) | [Model](https://huggingface.co/memoavatar/memo)_
+
+This repository contains the example inference script for the MEMO-preview model. The gif demo below is compressed. See our [project page](https://memoavatar.github.io) for full videos.
+
+<div style="width: 100%; text-align: center;">
+    <img src="https://github.com/memoavatar/memo/raw/main/assets/demo.gif" alt="Demo GIF" style="width: 100%; height: auto;">
+</div>
+
+## Installation
+
+```bash
+conda create -n memo python=3.10 -y
+conda activate memo
+conda install -c conda-forge ffmpeg -y
+pip install -e .
+```
+
+> Our code will download the checkpoint from Hugging Face automatically, and the models for face analysis and vocal separation will be downloaded to `misc_model_dir` of `configs/inference.yaml`. If you want to download the models manually, please download the checkpoint from [here](https://huggingface.co/memoavatar/memo) and specify the path in `model_name_or_path` of `configs/inference.yaml`.
+
+## Inference
+
+```bash
+python inference.py --config configs/inference.yaml --input_image <IMAGE_PATH> --input_audio <AUDIO_PATH> --output_dir <SAVE_PATH>
+```
+
+For example:
+
+```bash
+python inference.py --config configs/inference.yaml --input_image assets/examples/dicaprio.jpg --input_audio assets/examples/speech.wav --output_dir outputs
+```
+
+> We tested the code on H100 and RTX 4090 GPUs using CUDA 12. Under the default settings (fps=30, inference_steps=20), the inference time is around 1 second per frame on H100 and 2 seconds per frame on RTX 4090. We welcome community contributions to improve the inference speed or interfaces like ComfyUI.
+
+## Acknowledgement
+
+Our work is made possible thanks to high-quality open-source talking video datasets (including [HDTF](https://github.com/MRzzm/HDTF), [VFHQ](https://liangbinxie.github.io/projects/vfhq), [CelebV-HQ](https://celebv-hq.github.io), [MultiTalk](https://multi-talk.github.io), and [MEAD](https://wywu.github.io/projects/MEAD/MEAD.html)) and some pioneering works (such as [EMO](https://humanaigc.github.io/emote-portrait-alive) and [Hallo](https://github.com/fudan-generative-vision/hallo)).
+
+## Ethics Statement
+
+We acknowledge the potential of AI in generating talking videos, with applications spanning education, virtual assistants, and entertainment. However, we are equally aware of the ethical, legal, and societal challenges that misuse of this technology could pose. 
+
+To reduce potential risks, we have only open-sourced a preview model for research purposes. Demos on our website use publicly available materials. We welcome copyright concerns—please contact us if needed, and we will address issues promptly. Users are required to ensure that their actions align with legal regulations, cultural norms, and ethical standards. 
+
+It is strictly prohibited to use the model for creating malicious, misleading, defamatory, or privacy-infringing content, such as deepfake videos for political misinformation, impersonation, harassment, or fraud. We strongly encourage users to review generated content carefully, ensuring it meets ethical guidelines and respects the rights of all parties involved. Users must also ensure that their inputs (e.g., audio and reference images) and outputs are used with proper authorization. Unauthorized use of third-party intellectual property is strictly forbidden. 
+
+While users may claim ownership of content generated by the model, they must ensure compliance with copyright laws, particularly when involving public figures' likeness, voice, or other aspects protected under personality rights.
+
+## Citation
+
+If you find our work useful, please use the following citation:
+
+```bibtex
+@article{zheng2024memo,
+  title={MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation},
+  author={Longtao Zheng and Yifan Zhang and Hanzhong Guo and Jiachun Pan and Zhenxiong Tan and Jiahao Lu and Chuanxin Tang and Bo An and Shuicheng Yan},
+  journal={arXiv preprint arXiv:2412.04448},
+  year={2024}
+}
+```

models/checkpoints/memo/audio_proj/config.json

@@ -0,0 +1,4 @@
+{
+  "_class_name": "AudioProjModel",
+  "_diffusers_version": "0.31.0"
+}

models/checkpoints/memo/audio_proj/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb32c18e7890c6550e2312964a48f447b5e30cd449c25cfe06324842d6146f6e
+size 145861272

models/checkpoints/memo/diffusion_net/config.json

@@ -0,0 +1,87 @@
+{
+  "_center_input_sample": false,
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.31.0",
+  "_out_channels": 4,
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "audio_attention_dim": 768,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "DownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "emo_drop_rate": 0.05,
+  "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_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock3DCrossAttn",
+  "motion_module_kwargs": {
+    "attention_block_types": [
+      "Temporal_Self",
+      "Temporal_Self"
+    ],
+    "num_attention_heads": 8,
+    "num_transformer_block": 1,
+    "temporal_attention_dim_div": 1,
+    "temporal_position_encoding": true,
+    "temporal_position_encoding_max_len": 32
+  },
+  "motion_module_resolutions": [
+    1,
+    2,
+    4,
+    8
+  ],
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "unet_use_cross_frame_attention": false,
+  "unet_use_temporal_attention": false,
+  "up_block_types": [
+    "UpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D"
+  ],
+  "upcast_attention": false,
+  "use_inflated_groupnorm": true,
+  "use_linear_projection": false
+}

models/checkpoints/memo/diffusion_net/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7581d7e0663fd27a3c7b2b242a7af5eda89e57c67e3259017f8b77d83b930479
+size 6712434824

models/checkpoints/memo/image_proj/config.json

@@ -0,0 +1,4 @@
+{
+  "_class_name": "ImageProjModel",
+  "_diffusers_version": "0.31.0"
+}

models/checkpoints/memo/image_proj/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac89d81e17f120f752548d028b4a9a9ad4abca9401590436b5c8c26d8cd8537
+size 6310216

models/checkpoints/memo/misc/audio_emotion_classifier/config.json

@@ -0,0 +1,4 @@
+{
+  "_class_name": "AudioEmotionClassifierModel",
+  "_diffusers_version": "0.31.0"
+}

models/checkpoints/memo/misc/audio_emotion_classifier/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c8ca4bcfd1695efcf80398d13e4a5f365ebba0d70052f24a8c232ee50ee76d
+size 58827684

models/checkpoints/memo/misc/face_analysis/glintr100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab1d6435d639628a6f3e5008dd4f929edf4c4124b1a7169e1048f9fef534cdf
+size 260665334

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/1k3d68.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
+size 143607619

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/2d106det.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
+size 5030888

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64184e229b263107bc2b804c6625db1341ff2bb731874b0bcc2fe6544e0bc9ff
+size 3758596

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/genderage.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
+size 1322532

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/glintr100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab1d6435d639628a6f3e5008dd4f929edf4c4124b1a7169e1048f9fef534cdf
+size 260665334

models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/scrfd_10g_bnkps.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
+size 16923827

models/checkpoints/memo/misc/face_analysis/models.json

@@ -0,0 +1,13 @@
+{
+    "detection": [
+      "scrfd_10g_bnkps"
+    ],
+    "recognition": [
+      "glintr100"
+    ],
+    "analysis": [
+      "genderage",
+      "2d106det",
+      "1k3d68"
+    ]
+  }

models/checkpoints/memo/misc/face_analysis/models/1k3d68.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
+size 143607619

models/checkpoints/memo/misc/face_analysis/models/2d106det.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
+size 5030888

models/checkpoints/memo/misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64184e229b263107bc2b804c6625db1341ff2bb731874b0bcc2fe6544e0bc9ff
+size 3758596

models/checkpoints/memo/misc/face_analysis/models/genderage.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
+size 1322532

models/checkpoints/memo/misc/face_analysis/models/scrfd_10g_bnkps.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
+size 16923827

models/checkpoints/memo/misc/vocal_separator/Kim_Vocal_2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce74ef3b6a6024ce44211a07be9cf8bc6d87728cc852a68ab34eb8e58cde9c8b
+size 66759214