Top 6 HF - Par Pipeline Tag

Les 6 meilleurs modèles par catégorie de tâche (triés par downloads/jour)

179 modèles dans 39 catégories | Généré le 21/11/2026 23:33 UTC

179 modèles sélectionnés

#ModeleDL/JourParamspipelineFR
1 Comfy-Org/MiniMax-H3 290,641 ≈33.1B image-to-image —
2 Comfy-Org/MiniMax-H3-Image 280,687 ≈20.1B text-to-image —
3 unsloth/Inkling-2-Mini-GGUF 238,152 GGUF (inconnu) image-text-to-text —
4 Comfy-Org/MOSS-Image 162,317 ≈9.7B image-to-image —
5 ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF FR 155,196 GGUF (inconnu) text-generation ✓
6 Comfy-Org/Qwen-Image-2.1 FR 139,659 ≈8.8B text-to-image ✓
7 ai-coustics/quail-voice-focus 127,149 — audio-to-audio —
8 mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF FR 113,470 9.0B (GGUF) text-generation ✓
9 ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR 99,841 GGUF (inconnu) image-text-to-text ✓
10 sentence-transformers/all-MiniLM-L6-v2 96,716 23.0MB sentence-similarity —
11 Efficient-Large-Model/Open-H3-Regenerate-2K 88,986 — video-to-video —
12 SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR 86,067 GGUF (inconnu) image-text-to-text ✓
13 unsloth/Qwen3.8-27B-GGUF FR 75,320 ≈24.4B text-generation ✓
14 peasantsmith/Hy4-Flash-Maya-GGUF 74,894 GGUF (inconnu) image-text-to-text —
15 zai-org/GLM-5.3-Flash FR 72,736 321.3B image-text-to-text ✓
16 Qwen/Qwen3.8-27B-FP8 FR 66,173 27.8B image-text-to-text ✓
17 ornith-ai/Ornith-1.5-9B-GGUF 59,690 9.0B (GGUF) text-generation —
18 PrunaAI/P-Image-OSS-Comfy 55,005 ≈20.2B text-to-image —
19 Hearthscale/MiniMax-H3-Image-GGUF 53,872 GGUF (inconnu) text-to-image —
20 MiniMaxAI/MiniMax-H3-Image 50,929 ≈2.9B text-to-image —
21 MiniMaxAI/MiniMax-H3 FR 50,241 33.1B image-text-to-video ✓
22 VideoRebirthAI/hyperflow-h3-flash 48,189 — image-text-to-video —
23 unsloth/Qwen-Image-2.1-Turbo-GGUF FR 45,254 GGUF (inconnu) text-to-image ✓
24 mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF FR 44,758 9.0B (GGUF) text-generation ✓
25 ornith-ai/Ornith-1.5-35B-A3B-GGUF 42,249 35.0B (GGUF) · MoE MOE text-generation —
26 unsloth/MiniMax-H3-GGUF 32,850 GGUF (inconnu) image-text-to-video —
27 BAAI/bge-m3 FR 32,727 ≈0.6B sentence-similarity ✓
28 Comfy-Org/Z-Image-Turbo 28,624 ≈6.2B image-to-image —
29 black-forest-labs/flux-3-image-klein-comfy FR 25,380 ≈9.4B image-to-image ✓
30 Lightricks/LTX-2.5 FR 24,798 ≈21.0B image-to-video ✓
31 Comfy-Org/Wan-2.2 21,728 ≈17.3B image-to-video —
32 LiquidAI/LFM3-Omni-2B-GGUF FR 21,682 2.0B (GGUF) any-to-any ✓
33 OliviaRossi/Minimax-h3_Singularity-x-10Eros-Max_PRISM 20,169 ≈33.1B other —
34 hexgrad/Kokoro-82M 19,071 82.0M text-to-speech —
35 fidel1234/Krea2 19,041 ≈0.1B image-to-image —
36 Comfy-Org/RelayVSR 18,763 ≈5.2B unconditional-image-generation —
37 k2-fsa/OmniVoice FR 18,304 0.6B text-to-speech ✓
38 lightx2v/Minimax-h3-Turbo 17,082 ≈34.0B image-to-image —
39 google/gemma-4-E4B-it FR 16,161 8.0B any-to-any ✓
40 WarmBloodAban/Minimax-h3_Singularity 16,120 ≈33.1B image-to-video —
41 pnnbao-ump/VieNeu-TTS-v3-Turbo 13,745 0.1B text-to-speech —
42 Zyphra/ZONOS3-Mini FR 12,854 — text-to-speech ✓
43 unsloth/LTX-2.5-GGUF FR 11,287 GGUF (inconnu) image-to-video ✓
44 gradium/phonon-31m-en 10,813 41.0MB text-to-speech —
45 inclusionAI/invoker-render-1.0 10,722 33.1B video-to-video —
46 google/gemma-4-E2B-it FR 10,323 5.1B any-to-any ✓
47 Viggle/Viggle-Remake 9,387 — video-to-video —
48 google/embeddinggemma-2 FR 9,019 0.7B feature-extraction ✓
49 google/vit-base-patch16-224 8,901 87.0MB image-classification —
50 google/gemma-4-12B-it FR 8,545 12.0B any-to-any ✓
51 pyannote/speaker-diarization-community-1 8,156 — automatic-speech-recognition —
52 Pika-Labs/Pika-H3-Flex-Turbo-LoRA 8,077 — image-to-video —
53 Pika-Labs/Pika-H3-Flex 7,877 33.1B image-to-video —
54 lodestones/MOSS-Image-SFT-8-steps-dmd 7,614 5.1B other —
55 google/gemma-4-12B-it-qat-q4_0-gguf FR 7,036 12.0B (GGUF) any-to-any ✓
56 BennyDaBall/HyperFlow-H3-Flash-INT8-ComfyUI 6,980 ≈16.3B image-text-to-video —
57 microsoft/TRELLIS.2-4B FR 6,870 ≈1.3B image-to-3d ✓
58 zai-org/GLM-OCR FR 6,813 1.3B image-to-text ✓
59 litert-community/gemma-4-E2B-it-litert-lm FR 6,375 2.0B other ✓
60 openai/whisper-large-v3-turbo FR 5,979 0.8B automatic-speech-recognition ✓
61 sakasegawa/Haru-4B-GGUF FR 5,684 4.0B (GGUF) audio-to-audio ✓
62 google/gemma-4-E4B-it-qat-q4_0-gguf FR 5,674 4.0B (GGUF) any-to-any ✓
63 pyannote/speaker-diarization-3.1 5,537 — automatic-speech-recognition —
64 Qwen/Qwen3-ASR-1.7B FR 5,462 2.3B automatic-speech-recognition ✓
65 LiquidAI/d1-Omni-2B-GGUF FR 5,372 2.0B (GGUF) audio-text-to-text ✓
66 facebook/sam3 4,883 0.9B mask-generation —
67 ResembleAI/chatterbox FR 4,615 ≈1.1B text-to-speech ✓
68 Comfy-Org/Idol 4,379 ≈0.8B image-to-3d —
69 google/timesfm-3.0-pytorch 4,369 0.3B time-series-forecasting —
70 HAL-X-AI/THX-02 4,312 4.5B zero-shot-classification —
71 pyannote/segmentation-3.0 3,872 — voice-activity-detection —
72 nvidia/Kumo-Tabular 3,744 — other —
73 Comfy-Org/PAN2 3,250 ≈33.7B text-to-video —
74 pfnet/plamo-3-translate-2b-GGUF FR 2,995 2.0B (GGUF) translation ✓
75 nvidia/Nemotron-3-Diarization 2,994 99.0MB voice-activity-detection —
76 openai/whisper-large-v3 FR 2,927 1.5B automatic-speech-recognition ✓
77 openai/whisper-small FR 2,842 0.2B automatic-speech-recognition ✓
78 litert-community/gemma-4-E4B-it-litert-lm FR 2,695 4.0B other ✓
79 vllm-sr/d3-flash 2,423 8.4B zero-shot-classification —
80 drbaph/MiniMax-H3-Turbo-Lora-ComfyUI 2,380 — text-to-video —
81 akatz-ai/MiniMax-H3-Character-Swap-LoRA 2,281 — video-to-video —
82 google/embeddinggemma-300m FR 1,946 0.3B sentence-similarity ✓
83 larryvrh/MiniMax-H3-Turbo-Lora 1,879 — text-to-video —
84 ZhengmingYu/DMAD 1,861 ≈1.0B text-to-video —
85 unsloth/embeddinggemma-2-GGUF FR 1,766 GGUF (inconnu) feature-extraction ✓
86 speridlabs/idol 1,637 ≈0.7B image-to-3d —
87 facebook/dinov3-vitl16-pretrain-lvd1689m 1,497 0.3B image-feature-extraction —
88 fal/MiniMax-H3-Realism-People-LoRA 1,303 — image-text-to-video —
89 Remtir/AksonOCR-Lite 1,303 — image-to-text —
90 ZhengPeng7/BiRefNet 1,163 0.2B image-segmentation —
91 nvidia/personaplex-7b-v1 1,004 8.4B audio-to-audio —
92 higurashi-ai/Haru-4B FR 902 5.3B audio-to-audio ✓
93 mistralai/Timestral-209M 799 0.2B time-series-forecasting —
94 OpenMOSS-Team/MOSS-Transcribe-Diarize FR 795 0.9B audio-text-to-text ✓
95 stabilityai/stable-audio-3-medium 738 2.3B text-to-audio —
96 facebook/dinov3-vitb16-pretrain-lvd1689m 708 86.0MB image-feature-extraction —
97 LiconStudio/Minimax-H3-VBVR 645 ≈75.0MB other —
98 facebook/sam3.1 576 — mask-generation —
99 tencent/Hunyuan3D-2 562 ≈2.5B image-to-3d —
100 openai/privacy-filter 533 1.4B token-classification —
101 briaai/RMBG-2.0 521 0.2B image-segmentation —
102 pablodawson/MiniMax-H3-360-Orbit-LoRA 511 — image-text-to-video —
103 vllm-sr/d3-mini 507 4.5B zero-shot-classification —
104 nvidia/NVIDIA-NemotronLabs-RE-USE 460 10.0MB audio-to-audio —
105 stabilityai/stable-audio-3-small-sfx 434 0.6B text-to-audio —
106 baselabs/mammoth-1 402 27.4B text-classification —
107 ai-coustics/vad-voice-focus 379 — voice-activity-detection —
108 meituan-longcat/LongCat-Video-Avatar-1.6 379 ≈2.7B other —
109 facebook/dinov3-vits16-pretrain-lvd1689m 354 22.0MB image-feature-extraction —
110 ACE-Step/Ace-Step1.5 351 ≈1.5B text-to-audio —
111 pixai-labs/pixai-tagger-v1.0 350 0.5B image-classification —
112 Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render 341 22.0B video-to-video —
113 Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details 340 22.0B video-to-video —
114 ContinuousIntelligence/ci-proto 333 — time-series-forecasting —
115 kobimusic/dettato 322 15.0MB other —
116 ggml-org/Laya-GGUF 321 GGUF (inconnu) text-classification —
117 baselabs/elephant-1 316 9.4B text-classification —
118 nvidia/Nemotron-3.5-Embed-8B-BF16 FR 309 8.4B visual-document-retrieval ✓
119 Lightricks/LTX-2.5-Diffusers FR 293 19.0B text-to-video ✓
120 m-a-p/YuE2-3B 277 3.6B text-to-audio —
121 briaai/RMBG-3.0-Comfy 258 ≈8.2B image-segmentation —
122 Prior-Labs/tabpfn_3_5 255 ≈0.4B tabular-classification —
123 LiquidAI/d1-Omni-2B FR 243 2.2B audio-text-to-text ✓
124 convaiinnovations/laya 240 0.4B text-classification —
125 lerobot/smolvla_base 236 0.5B robotics —
126 tencent/Hunyuan3D-2.1 235 ≈0.6B image-to-3d —
127 elix3r/gemma4-12b-with-proj-ltx-2.5-GGUF FR 233 12.0B (GGUF) feature-extraction ✓
128 hyz317/HairDeck 210 ≈0.4B image-to-3d —
129 ai-coustics/tyto 207 — other —
130 MachinePulseAI/karpo-decision-31B 205 31.3B text-classification —
131 rayline-ai/ARC-1.0 204 0.6B text-classification —
132 minishlab/blink-8M 155 8.0MB feature-extraction —
133 stabilityai/stable-audio-3-small-music 153 0.6B text-to-audio —
134 datalab-to/indra-ocr FR 143 1.0MB image-to-text ✓
135 LiquidAI/Liquid-Codec FR 132 74.0MB feature-extraction ✓
136 minishlab/blink-multilingual-64M FR 130 64.0MB feature-extraction ✓
137 ai-coustics/quail-multi-speaker 125 — audio-to-audio —
138 apple/DepthPro2-focal 118 23.0MB depth-estimation —
139 tencent/Hy-MT2-1.8B FR 111 2.0B translation ✓
140 tencent/HunyuanVideo 110 — text-to-video —
141 facebook/dinov3-vith16plus-pretrain-lvd1689m 106 0.8B image-feature-extraction —
142 iapp/OpenThai2.1-OCR-Text-20261118 104 — image-to-text —
143 vllm-sr/d3-turbo 98 26.1B zero-shot-classification —
144 Ultralytics/YOLO26 FR 92 — object-detection ✓
145 tomaarsen/TinyCLIP-39M-PixelArt 72 83.0MB sentence-similarity —
146 kakaocorp/kanana-2-v-decide-3b-2611 68 3.7B zero-shot-classification —
147 tencent/WeMM-Video-2B 65 3.3B video-text-to-text —
148 tencent/WeMM-Video-35BA3B 60 36.2B video-text-to-text —
149 FrontiersMind/NandiBERT-150M FR 58 0.2B fill-mask ✓
150 tencent/WeMM-Video-9B 58 10.5B video-text-to-text —
151 openjev/openjev FR 51 27.4B zero-shot-classification ✓
152 MiniMaxAI/MiniMax-Music3 50 2.4B text-to-audio —
153 FrontiersMind/NandiBERT-450M FR 47 0.5B fill-mask ✓
154 ai-coustics/vad-multi-speaker 46 — voice-activity-detection —
155 apple/DepthPro2-S 40 24.0MB depth-estimation —
156 nvidia/Alpamayo2-Edge 37 2.7B robotics —
157 tencent/WeMM-Video-35BA3B-FP8 37 36.2B video-text-to-text —
158 charcot-ai/marimba 33 ≈52.0MB audio-classification —
159 apple/DepthPro2-H 28 0.9B depth-estimation —
160 kkt94/Llama-V-JEPA-LM-Qwen3-30B-A3B FR 26 32.4B / 3.0B MOE video-text-to-text ✓
161 apple/DepthPro2-L 23 0.3B depth-estimation —
162 apple/DepthPro2-B 22 97.0MB depth-estimation —
163 racineai/Jevol-2B 19 2.2B robotics —
164 briaai/RMBG-3.0 18 8.1B image-segmentation —
165 racineai/Jevol-0.6B 15 0.6B robotics —
166 Roboflow/rf-detr-large 15 34.0MB object-detection —
167 racineai/Jevol-0.9B 14 0.9B robotics —
168 facebook/dinov3-vit7b16-pretrain-lvd1689m 14 6.7B image-feature-extraction —
169 apple/DepthPro2-coreml 13 — depth-estimation —
170 gertelrina/aadd 12 — audio-classification —
171 desert-ant-labs/ear FR 8 — audio-classification ✓
172 tencent/WeVisForensics 7 — video-text-to-text —
173 knowledgator/gliformer-0.4b-v1.5 2 0.4B token-classification —
174 tencent/HY-Motion-1.0 1 — text-to-3d —
175 knowledgator/gliformer-2b-v1.5 1 2.0B token-classification —
176 inworld/sava 0 ≈26.0MB voice-activity-detection —
177 bageldotcom/Bagel-Robotics-1 0 — robotics —
178 iapp/OpenThai2.0-LATTE-WordSeg-Lite 0 — token-classification —
179 dbonet/iLTM 0 — tabular-classification —