aiplexdeveloper/Wan2.2-Animate-14B

By aiplexdeveloper · ↓ 9 · ♥ 0 · Updated 2025-10-06

What's in this repo

This page lists the files in aiplexdeveloper/Wan2.2-Animate-14B, including yolov10m.onnx, end2end.onnx, model.onnx.

3 ONNX models (.onnx files)
444 files, including 194 .bias, 69 .weight, 14 .json, 6 .png, 6 .safetensors, 4 .pt
Last updated 2025-10-06

ONNX files

File	Size	Download
process_checkpoint/det/yolov10m.onnx	—	Download
process_checkpoint/pose2d/vitpose_h_wholebody.onnx/end2end.onnx	—	Download
xlm-roberta-large/onnx/model.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Wan2.2

![](assets/logo.png)

💜 [Wan](https://wan.video) &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ [GitHub](https://github.com/Wan-Video/Wan2.2) &nbsp&nbsp  | &nbsp&nbsp🤗 [Hugging Face](https://huggingface.co/Wan-AI/)&nbsp&nbsp | &nbsp&nbsp🤖 [ModelScope](https://modelscope.cn/organization/Wan-AI)&nbsp&nbsp | &nbsp&nbsp 📑 [Paper](https://arxiv.org/abs/2503.20314) &nbsp&nbsp | &nbsp&nbsp 📑 [Blog](https://wan.video/welcome?spm=a2ty_o02.30011076.0.0.6c9ee41eCcluqg) &nbsp&nbsp |  &nbsp&nbsp 💬  [Discord](https://discord.gg/AKNgpMK4Yj)&nbsp&nbsp
  

📕 [使用指南(中文)](https://alidocs.dingtalk.com/i/nodes/jb9Y4gmKWrx9eo4dCql9LlbYJGXn6lpz)&nbsp&nbsp | &nbsp&nbsp 📘 [User Guide(English)](https://alidocs.dingtalk.com/i/nodes/EpGBa2Lm8aZxe5myC99MelA2WgN7R35y)&nbsp&nbsp | &nbsp&nbsp💬 [WeChat(微信)](https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg)&nbsp&nbsp

Wan: Open and Advanced Large-Scale Video Generative Models

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations:

👍 Effective MoE Architecture: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost.
👍 Cinematic-level Aesthetics: Wan2.2 incorporates meticulously curated aesthetic data, complete with detailed labels for lighting, composition, contrast, color tone, and more. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences.
👍 Complex Motion Generation: Compared to Wan2.1, Wan2.2 is trained on a significantly larger data, with +65.6% more images and +83.2% more videos. This expansion notably enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving TOP performance among all open-sourced and closed-sourced models.
👍 Efficient High-Definition Hybrid TI2V: Wan2.2 open-sources a 5B model built with our advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously.

Video Demos

    Your browser does not support the video tag.

🔥 Latest News!!

Sep 19, 2025: 💃 We introduct Wan2.2-Animate-14B, an unified model for character animation and replacement with holistic movement and expression replication. We released the model weights and inference code. And now you can try it on wan.video, ModelScope Studio or HuggingFace Space!
Aug 26, 2025: 🎵 We introduce Wan2.2-S2V-14B, an audio-driven cinematic video generation model, including inference code, model weights, and technical report! Now you can try it on wan.video, ModelScope Gradio or HuggingFace Gradio!
Jul 28, 2025: 👋 We have open a HF space using the TI2V-5B model. Enjoy!
Jul 28, 2025: 👋 Wan2.2 has been integrated into ComfyUI (CN | EN). Enjoy!
Jul 28, 2025: 👋 Wan2.2's T2V, I2V and TI2V have been integrated into Diffusers (T2V-A14B | I2V-A14B | TI2V-5B). Feel free to give it a try!
Jul 28, 2025: 👋 We've released the inference code and model weights of Wan2.2.
Sep 5, 2025: 👋 We add text-to-speech synthesis support with CosyVoice for Speech-to-Video generation task.

Community Works

If your research or project builds upon Wan2.1 or Wan2.2, and you would like more people to see it, please inform us.

DiffSynth-Studio provides comprehensive support for Wan 2.2, including low-GPU-memory layer-by-layer offload, FP8 quantization, sequence parallelism, LoRA training, full training.
Kijai's ComfyUI WanVideoWrapper is an alternative implementation of Wan models for ComfyUI. Thanks to its Wan-only focus, it's on the frontline of getting cutting edge optimizations and hot research features, which are often hard to integrate into ComfyUI quickly due to its more rigid structure.
Cache-dit offers Fully Cache Acceleration support for Wan2.2 MoE with DBCache, TaylorSeer and Cache CFG. Visit their example for more details.
FastVideo includes distilled Wan models with sparse attention that significanly speed up the inference time.

📑 Todo List

Wan2.2 Text-to-Video
- [x] Multi-GPU Inference code of the A14B and 14B models
- [x] Checkpoints of the A14B and 14B models
- [x] ComfyUI integration
- [x] Diffusers integration
Wan2.2 Image-to-Video
- [x] Multi-GPU Inference code of the A14B model
- [x] Checkpoints of the A14B model
- [x] ComfyUI integration
- [x] Diffusers integration
Wan2.2 Text-Image-to-Video
- [x] Multi-GPU Inference code of the 5B model
- [x] Checkpoints of the 5B model
- [x] ComfyUI integration
- [x] Diffusers integration
Wan2.2-S2V Speech-to-Video
- [x] Inference code of Wan2.2-S2V
- [x] Checkpoints of Wan2.2-S2V-14B
- [x] ComfyUI integration
- [x] Diffusers integration
Wan2.2-Animate Character Animation and Replacement
- [x] Inference code of Wan2.2-Animate
- [x] Checkpoints of Wan2.2-Animate
- [x] ComfyUI integration
- [ ] Diffusers integration

Run Wan2.2 Animate

Installation

Clone the repo:

git clone https://github.com/Wan-Video/Wan2.2.git
cd Wan2.2

Install dependencies:

# Ensure torch >= 2.4.0
# If the installation of `flash_attn` fails, try installing the other packages first and install `flash_attn` last
pip install -r requirements.txt
# If you want to use CosyVoice to synthesize speech for Speech-to-Video Generation, please install requirements_s2v.txt additionally
pip install -r requirements_s2v.txt

Model Download

Models	Download Links	Description
T2V-A14B	🤗 Huggingface 🤖 ModelScope	Text-to-Video MoE model, supports 480P & 720P
I2V-A14B	🤗 Huggingface 🤖 ModelScope	Image-to-Video MoE model, supports 480P & 720P
TI2V-5B	🤗 Huggingface 🤖 ModelScope	High-compression VAE, T2V+I2V, supports 720P
S2V-14B	🤗 Huggingface 🤖 ModelScope	Speech-to-Video model, supports 480P & 720P
Animate-14B	🤗 Huggingface 🤖 ModelScope	Character animation and replacement

Download models using huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-Animate-14B --local-dir ./Wan2.2-Animate-14B

Download models using modelscope-cli:

pip install modelscope
modelscope download Wan-AI/Wan2.2-Animate-14B --local_dir ./Wan2.2-Animate-14B

Run Wan-Animate-14B

Wan-Animate takes a video and a character image as input, and generates a video in either "animation" or "replacement" mode.

animation mode： The model generates a video of the character image that mimics the human motion in the input video.
replacement mode: The model replaces the character image with the input video.

Please visit our project page to see more examples and learn about the scenarios suitable for this model.

(1) Preprocessing

The input video should be preprocessed into several materials before be feed into the inference process. Please refer to the following processing flow, and more details about preprocessing can be found in UserGuider.

For animation

python ./wan/modules/animate/preprocess/preprocess_data.py \
    --ckpt_path ./Wan2.2-Animate-14B/process_checkpoint \
    --video_path ./examples/wan_animate/animate/video.mp4 \
    --refer_path ./examples/wan_animate/animate/image.jpeg \
    --save_path ./examples/wan_animate/animate/process_results \
    --resolution_area 1280 720 \
    --retarget_flag \
    --use_flux

For replacement

python ./wan/modules/animate/preprocess/preprocess_data.py \
    --ckpt_path ./Wan2.2-Animate-14B/process_checkpoint \
    --video_path ./examples/wan_animate/replace/video.mp4 \
    --refer_path ./examples/wan_animate/replace/image.jpeg \
    --save_path ./examples/wan_animate/replace/process_results \
    --resolution_area 1280 720 \
    --iterations 3 \
    --k 7 \
    --w_len 1 \
    --h_len 1 \
    --replace_flag

(2) Run in animation mode

Single-GPU inference

python generate.py --task animate-14B --ckpt_dir ./Wan2.2-Animate-14B/ --src_root_path ./examples/wan_animate/animate/process_results/ --refert_num 1

Multi-GPU inference using FSDP + DeepSpeed Ulysses

python -m torch.distributed.run --nnodes 1 --nproc_per_node 8 generate.py --task animate-14B --ckpt_dir ./Wan2.2-Animate-14B/ --src_root_path ./examples/wan_animate/animate/process_results/ --refert_num 1 --dit_fsdp --t5_fsdp --ulysses_size 8

(3) Run in replacement mode

Single-GPU inference

python generate.py --task animate-14B --ckpt_dir ./Wan2.2-Animate-14B/ --src_root_path ./examples/wan_animate/replace/process_results/ --refert_num 1 --replace_flag --use_relighting_lora

Multi-GPU inference using FSDP + DeepSpeed Ulysses

python -m torch.distributed.run --nnodes 1 --nproc_per_node 8 generate.py --task animate-14B --ckpt_dir ./Wan2.2-Animate-14B/ --src_root_path ./examples/wan_animate/replace/process_results/src_pose.mp4  --refert_num 1 --replace_flag --use_relighting_lora --dit_fsdp --t5_fsdp --ulysses_size 8

💡 If you're using Wan-Animate, we do not recommend using LoRA models trained on Wan2.2, since weight changes during training may lead to unexpected behavior.

Computational Efficiency on Different GPUs

We test the computational efficiency of different Wan2.2 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB).

![](assets/comp_effic.png)

The parameter settings for the tests presented in this table are as follows: (1) Multi-GPU: 14B: --ulysses_size 4/8 --dit_fsdp --t5_fsdp, 5B: --ulysses_size 4/8 --offload_model True --convert_model_dtype --t5_cpu; Single-GPU: 14B: --offload_model True --convert_model_dtype, 5B: --offload_model True --convert_model_dtype --t5_cpu (--convert_model_dtype converts model parameter types to config.param_dtype); (2) The distributed testing utilizes the built-in FSDP and Ulysses implementations, with FlashAttention3 deployed on Hopper architecture GPUs; (3) Tests were run without the --use_prompt_extend flag; (4) Reported results are the average of multiple samples taken after the warm-up phase.

Introduction of Wan2.2

Wan2.2 builds on the foundation of Wan2.1 with notable improvements in generation quality and model capability. This upgrade is driven by a series of key technical innovations, mainly including the Mixture-of-Experts (MoE) architecture, upgraded training data, and high-compression video generation.

(1) Mixture-of-Experts (MoE) Architecture

Wan2.2 introduces Mixture-of-Experts (MoE) architecture into the video generation diffusion model. MoE has been widely validated in large language models as an efficient approach to increase total model parameters while keeping inference cost nearly unchanged. In Wan2.2, the A14B model series adopts a two-expert design tailored to the denoising process of diffusion models: a high-noise expert for the early stages, focusing on overall layout; and a low-noise expert for the later stages, refining video details. Each expert model has about 14B parameters, resulting in a total of 27B parameters but only 14B active parameters per step, keeping inference computation and GPU memory nearly unchanged.

![](assets/moe_arch.png)

The transition point between the two experts is determined by the signal-to-noise ratio (SNR), a metric that decreases monotonically as the denoising step $t$ increases. At the beginning of the denoising process, $t$ is large and the noise level is high, so the SNR is at its minimum, denoted as ${SNR}{min}$. In this stage, the high-noise expert is activated. We define a threshold step ${t}{moe}$ corresponding to half of the ${SNR}_{min}$, and switch to the low-noise expert when $t

To validate the effectiveness of the MoE architecture, four settings are compared based on their validation loss curves. The baseline Wan2.1 model does not employ the MoE architecture. Among the MoE-based variants, the Wan2.1 & High-Noise Expert reuses the Wan2.1 model as the low-noise expert while uses the Wan2.2's high-noise expert, while the Wan2.1 & Low-Noise Expert uses Wan2.1 as the high-noise expert and employ the Wan2.2's low-noise expert. The Wan2.2 (MoE) (our final version) achieves the lowest validation loss, indicating that its generated video distribution is closest to ground-truth and exhibits superior convergence.

(2) Efficient High-Definition Hybrid TI2V

To enable more efficient deployment, Wan2.2 also explores a high-compression design. In addition to the 27B MoE models, a 5B dense model, i.e., TI2V-5B, is released. It is supported by a high-compression Wan2.2-VAE, which achieves a $T\times H\times W$ compression ratio of $4\times16\times16$, increasing the overall compression rate to 64 while maintaining high-quality video reconstruction. With an additional patchification layer, the total compression ratio of TI2V-5B reaches $4\times32\times32$. Without specific optimization, TI2V-5B can generate a 5-second 720P video in under 9 minutes on a single consumer-grade GPU, ranking among the fastest 720P@24fps video generation models. This model also natively supports both text-to-video and image-to-video tasks within a single unified framework, covering both academic research and practical applications.

![](assets/vae.png)

Comparisons to SOTAs

We compared Wan2.2 with leading closed-source commercial models on our new Wan-Bench 2.0, evaluating performance across multiple crucial dimensions. The results demonstrate that Wan2.2 achieves superior performance compared to these leading models.

![](assets/performance.png)

Citation

If you find our work helpful, please cite us.

@article{wan2025,
      title={Wan: Open and Advanced Large-Scale Video Generative Models}, 
      author={Team Wan and Ang Wang and Baole Ai and Bin Wen and Chaojie Mao and Chen-Wei Xie and Di Chen and Feiwu Yu and Haiming Zhao and Jianxiao Yang and Jianyuan Zeng and Jiayu Wang and Jingfeng Zhang and Jingren Zhou and Jinkai Wang and Jixuan Chen and Kai Zhu and Kang Zhao and Keyu Yan and Lianghua Huang and Mengyang Feng and Ningyi Zhang and Pandeng Li and Pingyu Wu and Ruihang Chu and Ruili Feng and Shiwei Zhang and Siyang Sun and Tao Fang and Tianxing Wang and Tianyi Gui and Tingyu Weng and Tong Shen and Wei Lin and Wei Wang and Wei Wang and Wenmeng Zhou and Wente Wang and Wenting Shen and Wenyuan Yu and Xianzhong Shi and Xiaoming Huang and Xin Xu and Yan Kou and Yangyu Lv and Yifei Li and Yijing Liu and Yiming Wang and Yingya Zhang and Yitong Huang and Yong Li and You Wu and Yu Liu and Yulin Pan and Yun Zheng and Yuntao Hong and Yupeng Shi and Yutong Feng and Zeyinzi Jiang and Zhen Han and Zhi-Fan Wu and Ziyu Liu},
      journal = {arXiv preprint arXiv:2503.20314},
      year={2025}
}

License Agreement

The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license.

Acknowledgements

We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research.

Contact Us

If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!

Model info

diffusers

diffusers onnx safetensors arxiv:2503.20314 license:apache-2.0 region:us

↓ 9 ♥ 0

Created: 2025-10-06

Updated: 2025-10-06

View on Hugging Face

Files (444)

.gitattributes

.msc

.mv

README.md

Wan2.1_VAE.pth

assets/comp_effic.png

assets/logo.png

assets/moe_2.png

assets/moe_arch.png

assets/performance.png

assets/vae.png

config.json

configuration.json

diffusion_pytorch_model-00001-of-00004.safetensors

diffusion_pytorch_model-00002-of-00004.safetensors

diffusion_pytorch_model-00003-of-00004.safetensors

diffusion_pytorch_model-00004-of-00004.safetensors

diffusion_pytorch_model.safetensors.index.json

google/umt5-xxl/special_tokens_map.json

google/umt5-xxl/spiece.model

google/umt5-xxl/tokenizer.json

google/umt5-xxl/tokenizer_config.json

models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth

models_t5_umt5-xxl-enc-bf16.pth

process_checkpoint/det/yolov10m.onnx ONNX

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.0.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.1.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.10.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.11.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.12.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.13.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.14.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.15.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.16.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.17.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.18.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.19.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.2.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.20.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.21.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.22.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.23.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.24.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.25.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.26.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.27.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.28.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.29.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.3.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.30.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.31.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.4.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.5.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.6.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.7.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.8.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.attn.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.attn.qkv.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.mlp.fc1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.mlp.fc2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.norm1.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.norm1.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.norm2.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.blocks.9.norm2.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.last_norm.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.last_norm.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.patch_embed.proj.bias

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/backbone.patch_embed.proj.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/end2end.onnx ONNX

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/keypoint_head.deconv_layers.0.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/keypoint_head.deconv_layers.3.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/keypoint_head.final_layer.weight

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__Add_2802

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__Add_2803

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2804

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2809

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2810

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2811

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2812

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2817

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2818

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2819

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2820

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2825

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2826

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2827

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2828

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2833

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2834

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2835

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2836

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2841

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2842

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2843

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2844

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2849

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2850

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2851

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2852

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2857

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2858

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2859

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2860

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2865

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2866

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2867

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2868

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2873

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2874

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2875

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2876

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2881

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2882

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2883

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2884

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2889

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2890

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2891

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2892

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2897

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2898

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2899

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2900

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2905

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2906

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2907

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2908

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2913

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2914

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2915

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2916

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2921

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2922

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2923

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2924

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2929

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2930

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2931

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2932

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2937

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2938

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2939

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2940

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2945

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2946

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2947

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2948

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2953

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2954

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2955

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2956

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2961

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2962

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2963

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2964

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2969

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2970

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2971

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2972

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2977

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2978

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2979

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2980

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2985

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2986

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2987

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2988

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2993

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2994

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2995

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_2996

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3001

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3002

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3003

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3004

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3009

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3010

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3011

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3012

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3017

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3018

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3019

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3020

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3025

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3026

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3027

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3028

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3033

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3034

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3035

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3036

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3041

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3042

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3043

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3044

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3049

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3050

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3051

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3052

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3057

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3058

process_checkpoint/pose2d/vitpose_h_wholebody.onnx/onnx__MatMul_3059

process_checkpoint/sam2/download_ckpts.sh

process_checkpoint/sam2/sam2_hiera_base_plus.pt

process_checkpoint/sam2/sam2_hiera_large.pt

process_checkpoint/sam2/sam2_hiera_small.pt

process_checkpoint/sam2/sam2_hiera_tiny.pt

relighting_lora.ckpt

relighting_lora/README.md

relighting_lora/adapter_config.json

relighting_lora/adapter_model.safetensors

xlm-roberta-large/README.md

xlm-roberta-large/config.json

xlm-roberta-large/configuration.json

xlm-roberta-large/flax_model.msgpack

xlm-roberta-large/model.safetensors

xlm-roberta-large/onnx/config.json

xlm-roberta-large/onnx/model.onnx ONNX

xlm-roberta-large/onnx/model.onnx_data

xlm-roberta-large/onnx/sentencepiece.bpe.model

xlm-roberta-large/onnx/special_tokens_map.json

xlm-roberta-large/onnx/tokenizer.json

xlm-roberta-large/onnx/tokenizer_config.json

xlm-roberta-large/pytorch_model.bin

xlm-roberta-large/sentencepiece.bpe.model

xlm-roberta-large/tf_model.h5

xlm-roberta-large/tokenizer.json

Related models

More from aiplexdeveloper

No other models by this author.

More models

No task type declared.