Improvements Collection by powmod Aug 20 - peculiar-ragdoll/Qwen-Sharp-Chat-Templates Updated Oct 10 • 511
vals Collection by rainday333 Aug 20 - onnx-community/pyannote-segmentation-3.0 Updated Jul 8, 2025 • 22.5k • 44
WorldReasonBench WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Collection by UniX-Lab Aug 20 - WorldReasonBench/WorldReasonBench Viewer • Updated May 7 • 436 • 88 • 3 WorldReasonBench/WorldRewardBench Viewer • Updated May 6 • 5.97k • 3.27k • 4 WorldReasonBench/WorldRewardBenchSubset Viewer • Updated May 6 • 1.78k • 55 • 2
Cyit Collection by Liranvard Sep 19 - RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-FP8 Text Generation • 1.4T • Updated Sep 16 • 164 • 7 unsloth/Qwen3.8-27B-GGUF 27B • Updated 8 days ago • 7.14M • 6.24k ornith-ai/Ornith-1.5-9B Text Generation • 10B • Updated Aug 23 • 603k • 439 ornith-ai/Ornith-1.5-35B-A3B Text Generation • 36B • Updated Aug 23 • 351k • 817
Image editing and enhancement demos Instruction-driven editing, outpainting and upscaling: give it an image and a sentence describing the change. Collection by wavespeed Sep 2 - Running 5 Qwen-Image-Edit 🖼 5 Reference for Qwen-Image-Edit, instruction-based editing Running 1 HiDream-E1 Full 🖼 1 Image editing built on HiDream-I1. Running FIBO Edit 🖼 Bria's FIBO editing model, trained on licensed data. Running Nano Banana Pro Edit 🖼 Instruction-driven editing with Nano Banana Pro.
German audio datasets Collection by q1805 Aug 27 - facebook/multilingual_librispeech Viewer • Updated Aug 12, 2024 • 1.49M • 36.2k • 201 D4ve-R/bundestag-asr Viewer • Updated Jun 9, 2024 • 250k • 415 • 3 q1805/german-pronuncheck-mega-dataset Viewer • Updated Aug 20 • 1.34M • 252 q1805/german-golden-audio_speech-IPA Viewer • Updated Aug 26 • 1.35k • 55
StreamOPD StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Collection by UniX-Lab 18 days ago 1 UniX-Lab/StreamOPD-4B-ST-CueGate Video-Text-to-Text • 5B • Updated Aug 18 • 39 • 4 UniX-Lab/StreamOPD-Data Viewer • Updated 18 days ago • 76.3k • 314 • 3 StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 10
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 10
Local | Agentic coding workflows | 16 GB Limit Collection by cut2kill Aug 20 - Qwen/Qwen2.5-Coder-14B-Instruct-GGUF Text Generation • 15B • Updated Nov 12, 2024 • 195k • 282 mistralai/Devstral-Small-2-24B-Instruct-2512 24B • Updated Jul 15 • 23.9k • 716 zai-org/glm-4-9b-chat 9B • Updated Mar 13, 2025 • 38.2k • 1.33k unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF 24B • Updated Dec 15, 2025 • 153k • 200
Video generation demos Text-to-video, image-to-video and audio-driven avatar Spaces: Wan, Veo, Sora, Seedance, Hailuo and Vidu. Collection by wavespeed Aug 20 - Running 20 Wan 2.2 🎞 20 Reference for Wan 2.2, Alibaba's open video models Running Wan2.2-S2V 🗣 Reference for Wan2.2-S2V, audio-driven video generation Running 42 Wan 2.1 Ultra Fast (image to video) 🎬 42 Wan 2.1 image-to-video at 480p, tuned for speed. Running 10 Wan 2.1 VACE 14B 🎬 10 VACE: all-in-one video creation and editing.
Text-to-image demos Bring-your-own-key Spaces for hosted text-to-image models, plus reference pages for the open-weight ones. No key is stored. Collection by wavespeed Sep 2 - Running 50 HiDream Arena ⚖ 50 One prompt, three models, side by side. Running Nano Banana Pro 🖼 Google's Nano Banana Pro, text to image. Running Seedream 4.0 🖼 ByteDance's image model. Text to image, up to 4K. Running 7 Seedream 4.5 🖼 7 The updated Seedream checkpoint from ByteDance.
Improvements Collection by powmod Aug 20 - peculiar-ragdoll/Qwen-Sharp-Chat-Templates Updated Oct 10 • 511
German audio datasets Collection by q1805 Aug 27 - facebook/multilingual_librispeech Viewer • Updated Aug 12, 2024 • 1.49M • 36.2k • 201 D4ve-R/bundestag-asr Viewer • Updated Jun 9, 2024 • 250k • 415 • 3 q1805/german-pronuncheck-mega-dataset Viewer • Updated Aug 20 • 1.34M • 252 q1805/german-golden-audio_speech-IPA Viewer • Updated Aug 26 • 1.35k • 55
vals Collection by rainday333 Aug 20 - onnx-community/pyannote-segmentation-3.0 Updated Jul 8, 2025 • 22.5k • 44
StreamOPD StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Collection by UniX-Lab 18 days ago 1 UniX-Lab/StreamOPD-4B-ST-CueGate Video-Text-to-Text • 5B • Updated Aug 18 • 39 • 4 UniX-Lab/StreamOPD-Data Viewer • Updated 18 days ago • 76.3k • 314 • 3 StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 10
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 10
WorldReasonBench WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Collection by UniX-Lab Aug 20 - WorldReasonBench/WorldReasonBench Viewer • Updated May 7 • 436 • 88 • 3 WorldReasonBench/WorldRewardBench Viewer • Updated May 6 • 5.97k • 3.27k • 4 WorldReasonBench/WorldRewardBenchSubset Viewer • Updated May 6 • 1.78k • 55 • 2
Local | Agentic coding workflows | 16 GB Limit Collection by cut2kill Aug 20 - Qwen/Qwen2.5-Coder-14B-Instruct-GGUF Text Generation • 15B • Updated Nov 12, 2024 • 195k • 282 mistralai/Devstral-Small-2-24B-Instruct-2512 24B • Updated Jul 15 • 23.9k • 716 zai-org/glm-4-9b-chat 9B • Updated Mar 13, 2025 • 38.2k • 1.33k unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF 24B • Updated Dec 15, 2025 • 153k • 200
Cyit Collection by Liranvard Sep 19 - RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-FP8 Text Generation • 1.4T • Updated Sep 16 • 164 • 7 unsloth/Qwen3.8-27B-GGUF 27B • Updated 8 days ago • 7.14M • 6.24k ornith-ai/Ornith-1.5-9B Text Generation • 10B • Updated Aug 23 • 603k • 439 ornith-ai/Ornith-1.5-35B-A3B Text Generation • 36B • Updated Aug 23 • 351k • 817
Video generation demos Text-to-video, image-to-video and audio-driven avatar Spaces: Wan, Veo, Sora, Seedance, Hailuo and Vidu. Collection by wavespeed Aug 20 - Running 20 Wan 2.2 🎞 20 Reference for Wan 2.2, Alibaba's open video models Running Wan2.2-S2V 🗣 Reference for Wan2.2-S2V, audio-driven video generation Running 42 Wan 2.1 Ultra Fast (image to video) 🎬 42 Wan 2.1 image-to-video at 480p, tuned for speed. Running 10 Wan 2.1 VACE 14B 🎬 10 VACE: all-in-one video creation and editing.
Image editing and enhancement demos Instruction-driven editing, outpainting and upscaling: give it an image and a sentence describing the change. Collection by wavespeed Sep 2 - Running 5 Qwen-Image-Edit 🖼 5 Reference for Qwen-Image-Edit, instruction-based editing Running 1 HiDream-E1 Full 🖼 1 Image editing built on HiDream-I1. Running FIBO Edit 🖼 Bria's FIBO editing model, trained on licensed data. Running Nano Banana Pro Edit 🖼 Instruction-driven editing with Nano Banana Pro.
Text-to-image demos Bring-your-own-key Spaces for hosted text-to-image models, plus reference pages for the open-weight ones. No key is stored. Collection by wavespeed Sep 2 - Running 50 HiDream Arena ⚖ 50 One prompt, three models, side by side. Running Nano Banana Pro 🖼 Google's Nano Banana Pro, text to image. Running Seedream 4.0 🖼 ByteDance's image model. Text to image, up to 4K. Running 7 Seedream 4.5 🖼 7 The updated Seedream checkpoint from ByteDance.