# Hunyuan

Source: [Hunyuan](<https://www.sota2.com/research/dataset/hunyuan>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 1. This is an index page, not the full collection.

- [Text-to-Video Generation on HunyuanVideo](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo.md>): Text-to-Video Generation; HunyuanVideo.

- [Instance Segmentation on HunyuanWorld 1.0](<https://www.sota2.com/research/sota/instance-segmentation-on-hunyuanworld-1-0.md>): Instance Segmentation; HunyuanWorld 1.0.

- [Text-to-Video Generation on HunyuanVideo (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-test.md>): Text-to-Video Generation; HunyuanVideo (test).

- [Text-to-Video Generation on VBench HunyuanVideo (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-hunyuanvideo-test.md>): text-to-video generation; VBench HunyuanVideo (test).

- [AI-generated video detection on Our Dataset HunyuanVideo](<https://www.sota2.com/research/sota/ai-generated-video-detection-on-our-dataset-hunyuanvideo.md>): AI-generated video detection; Our Dataset HunyuanVideo.

- [Video Generation on VBench HunyuanVideo](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuanvideo.md>): Video Generation; VBench HunyuanVideo.

- [Video Generation on HunyuanVideo 129 frames 544P](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-129-frames-544p.md>): Video Generation; HunyuanVideo 129 frames 544P.

- [Text-to-Video Generation Inference on T2V Models HunyuanVideo, Wan2.2](<https://www.sota2.com/research/sota/text-to-video-generation-inference-on-t2v-models-hunyuanvideo-wan2-2.md>): Text-to-Video Generation Inference; T2V Models HunyuanVideo, Wan2.2.

- [Image-to-Video Watermarking on VBench HunyuanVideo I2V 2.0](<https://www.sota2.com/research/sota/image-to-video-watermarking-on-vbench-hunyuanvideo-i2v-2-0.md>): Image-to-Video Watermarking; VBench HunyuanVideo I2V 2.0.

- [Text-to-Video Watermarking on VBench HunyuanVideo T2V 2.0](<https://www.sota2.com/research/sota/text-to-video-watermarking-on-vbench-hunyuanvideo-t2v-2-0.md>): Text-to-Video Watermarking; VBench HunyuanVideo T2V 2.0.

- [Text-to-Video generation on HunyuanVideo 13B CFG = 6.0, 720 × 1280p, frames = 60 (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-13b-cfg-6-0-720-1280p-frames-60-test.md>): Text-to-Video generation; HunyuanVideo 13B CFG = 6.0, 720 × 1280p, frames = 60 (test).

- [Video Generation on HunyuanVideo 13B (test)](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-13b-test.md>): Video Generation; HunyuanVideo 13B (test).

- [Video Generation on Hunyuan Video](<https://www.sota2.com/research/sota/video-generation-on-hunyuan-video.md>): Video Generation; Hunyuan Video.

- [Image-to-World generation on HunyuanVoyager-13B (test)](<https://www.sota2.com/research/sota/image-to-world-generation-on-hunyuanvoyager-13b-test.md>): Image-to-World generation; HunyuanVoyager-13B (test).

- [Text-to-video generation on HunyuanVideo 544p × 860p, 17 frames](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-544p-860p-17-frames.md>): Text-to-video generation; HunyuanVideo 544p × 860p, 17 frames.

- [Talking Head Generation on HunyuanVideo Avatar](<https://www.sota2.com/research/sota/talking-head-generation-on-hunyuanvideo-avatar.md>): Talking Head Generation; HunyuanVideo Avatar.

- [Video Generation on HunyuanVideo 480p (129 Frames)](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-480p-129-frames.md>): Video Generation; HunyuanVideo 480p, 129 Frames.

- [Video Generation on VBench HunyuanVideo (VBench %, Latency, FLOPs)](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuanvideo-vbench-percent-latency-flops.md>): Video Generation; VBench HunyuanVideo.

- [Text-to-Video Generation on HunyuanVideo VBench prompts (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-vbench-prompts-test.md>): Text-to-Video Generation; HunyuanVideo VBench prompts (test).

- [Text-to-video generation on VBench Hunyuan 480P 65 frames (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-hunyuan-480p-65-frames-test.md>): Text-to-video generation; VBench Hunyuan 480P 65 frames (test).

- [Video Generation on HunyuanVideo 720p 129 Frames](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-720p-129-frames.md>): Video Generation; HunyuanVideo 720p 129 Frames.

- [AIGI Detection on HunyuanImage 3.0 (test)](<https://www.sota2.com/research/sota/aigi-detection-on-hunyuanimage-3-0-test.md>): AIGI Detection; HunyuanImage 3.0 (test).

- [Text-to-Video on VBench Hunyuan 13B 720P (test)](<https://www.sota2.com/research/sota/text-to-video-on-vbench-hunyuan-13b-720p-test.md>): Text-to-Video; VBench Hunyuan 13B 720P (test).

- [Video Generation on HunyuanVideo 480P (65 frames, test)](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-480p-65-frames-test.md>): Video Generation; HunyuanVideo 480P, 65 frames 1.0 (test).

- [Video Extrapolation on VBench HunyuanVideo with 5x extrapolation v1.0 (test)](<https://www.sota2.com/research/sota/video-extrapolation-on-vbench-hunyuanvideo-with-5x-extrapolation-v1-0-test.md>): Video Extrapolation; VBench HunyuanVideo with 5x extrapolation v1.0 (test).

- [Video Extrapolation on VBench HunyuanVideo with 2x extrapolation v1.0 (test)](<https://www.sota2.com/research/sota/video-extrapolation-on-vbench-hunyuanvideo-with-2x-extrapolation-v1-0-test.md>): Video Extrapolation; VBench HunyuanVideo with 2x extrapolation v1.0 (test).

- [Mesh Generation on Hunyuan3D Dense Meshes 2.5](<https://www.sota2.com/research/sota/mesh-generation-on-hunyuan3d-dense-meshes-2-5.md>): Mesh Generation; Hunyuan3D Dense Meshes 2.5.

- [Mesh Reconstruction on Hunyuan3D Dense Meshes 2.5 (test)](<https://www.sota2.com/research/sota/mesh-reconstruction-on-hunyuan3d-dense-meshes-2-5-test.md>): Mesh Reconstruction; Hunyuan3D Dense Meshes 2.5 (test).

- [Text-to-video generation on HunyuanVideo 480p × 640p, 45 frames](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-480p-640p-45-frames.md>): Text-to-video generation; HunyuanVideo 480p × 640p, 45 frames.

- [Video Generation on HunyuanVideo 117 frames (test)](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-117-frames-test.md>): Video Generation; HunyuanVideo 117 frames (test).

- [Text-to-Video on HunyuanVideo 13B 129 Frames 720p](<https://www.sota2.com/research/sota/text-to-video-on-hunyuanvideo-13b-129-frames-720p.md>): Text-to-Video; HunyuanVideo 13B 129 Frames 720p.

- [Image-to-Video on HunyuanVideo 81 frames, 480p 1.5](<https://www.sota2.com/research/sota/image-to-video-on-hunyuanvideo-81-frames-480p-1-5.md>): Image-to-Video; HunyuanVideo 81 frames, 480p 1.5.

- [Video Generation on VBench & VisionReward HunyuanVideo 120f](<https://www.sota2.com/research/sota/video-generation-on-vbench-and-visionreward-hunyuanvideo-120f.md>): Video Generation; VBench & VisionReward HunyuanVideo 120f.

- [Video Quality Assessment on CompressedVQA HunyuanVideo](<https://www.sota2.com/research/sota/video-quality-assessment-on-compressedvqa-hunyuanvideo.md>): Video Quality Assessment; CompressedVQA HunyuanVideo.

- [Image-to-Video Generation on HunyuanVideo 1.5](<https://www.sota2.com/research/sota/image-to-video-generation-on-hunyuanvideo-1-5.md>): Image-to-Video Generation; HunyuanVideo 1.5.

- [Video Generation on VBench Hunyuan Video](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuan-video.md>): Video Generation; VBench Hunyuan Video.

- [Model Compression on Hunyuan3D 2mini (test)](<https://www.sota2.com/research/sota/model-compression-on-hunyuan3d-2mini-test.md>): Model Compression; Hunyuan3D 2mini (test).

- [Model Compression on Hunyuan3D 2.0 (test)](<https://www.sota2.com/research/sota/model-compression-on-hunyuan3d-2-0-test.md>): Model Compression; Hunyuan3D 2.0 (test).

- [Text-to-Video Generation on HunyuanVideo 1.5](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuanvideo-1-5.md>): Text-to-Video Generation; HunyuanVideo 1.5.

- [Text-to-Video Generation on Hunyuan 13B](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuan-13b.md>): Text-to-Video Generation; Hunyuan 13B.

- [Text-to-Video Generation on VBench Hunyuan 13B 720P (50 Sample Subset)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-hunyuan-13b-720p-50-sample-subset.md>): Text-to-Video Generation; VBench Hunyuan 13B, 720P, T2V (subset of 50 samples).

- [Text-to-Video on HunyuanVideo 480P](<https://www.sota2.com/research/sota/text-to-video-on-hunyuanvideo-480p.md>): Text-to-Video; HunyuanVideo 480P.

- [Video Generation on VBench & VisionReward HunyuanVideo 241f](<https://www.sota2.com/research/sota/video-generation-on-vbench-and-visionreward-hunyuanvideo-241f.md>): Video Generation; VBench & VisionReward HunyuanVideo 241f.

- [Video Generation on VBench HunyuanVideo 1280×720](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuanvideo-1280-720.md>): Video Generation; VBench HunyuanVideo 1280×720.

- [Text-to-Video Generation on Hunyuan-13B (720P)](<https://www.sota2.com/research/sota/text-to-video-generation-on-hunyuan-13b-720p.md>): Text-to-Video Generation; Hunyuan-13B Text-to-Video 720P.

- [Visual Harmfulness Evaluation on HunyuanVideo](<https://www.sota2.com/research/sota/visual-harmfulness-evaluation-on-hunyuanvideo.md>): Visual Harmfulness Evaluation; HunyuanVideo.

- [Video Generation on HunyuanVideo 17 frames, 544P](<https://www.sota2.com/research/sota/video-generation-on-hunyuanvideo-17-frames-544p.md>): Video Generation; HunyuanVideo 17 frames, 544P.

- [Video Generation on VBench Hunyuan-13B Text-to-Video 720P](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuan-13b-text-to-video-720p.md>): Video Generation; VBench Hunyuan-13B Text-to-Video 720P.

- [Video Generation on VBench HunyuanVideo-T2V-13B](<https://www.sota2.com/research/sota/video-generation-on-vbench-hunyuanvideo-t2v-13b.md>): Video Generation; VBench HunyuanVideo-T2V-13B.

- [Video Generation on User Preference Study Hunyuan-Video Human Evaluation 1.5](<https://www.sota2.com/research/sota/video-generation-on-user-preference-study-hunyuan-video-human-evaluation-1-5.md>): Video Generation; User Preference Study Hunyuan-Video Human Evaluation 1.5.

- [Red-teaming on Hunyuan-Video Seed-free generation](<https://www.sota2.com/research/sota/red-teaming-on-hunyuan-video-seed-free-generation.md>): Red-teaming; Hunyuan-Video Seed-free generation.

- [Watermark Extraction on HunyuanVideo I2V (Temporal Disturbance, 512x16 bits)](<https://www.sota2.com/research/sota/watermark-extraction-on-hunyuanvideo-i2v-temporal-disturbance-512x16-bits.md>): Watermark extraction; HunyuanVideo I2V (Temporal Disturbance, 512x16 bits).

- [Watermark Extraction on HunyuanVideo I2V (Spatial Disturbance, 512 bits)](<https://www.sota2.com/research/sota/watermark-extraction-on-hunyuanvideo-i2v-spatial-disturbance-512-bits.md>): Watermark extraction; HunyuanVideo I2V (Spatial Disturbance, 512 bits).

- [Image-to-3D Generation on Hunyuan3D 3.0 (test)](<https://www.sota2.com/research/sota/image-to-3d-generation-on-hunyuan3d-3-0-test.md>): Image-to-3D Generation; Hunyuan3D 3.0 (test).