Bridging the Data Provenance Gap Across Text, Speech and Video Paper β’ 2412.17847 β’ Published Dec 19, 2024 β’ 10
view post Post 5168 Researchers developed Sonic AI enabling precise facial animation from speech cues π§ Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis See translation 1 reply Β· π 8 8 π₯ 6 6 π 2 2 π§ 1 1 + Reply
view post Post 4296 I created my own AI image and video from scratch using the fal.ai platform π«Workflow: Flux Lora Training + Upscale + Kling AI(1.6) See translation 6 replies Β· π₯ 7 7 π 3 3 π 3 3 + Reply
view post Post 4499 I am training a controlnet model for Flux. And some of my experiences:Checkpoint-10000:https://x.com/kadirnar_ai/status/1829831750471606668Checkpoint-12000:https://x.com/kadirnar_ai/status/1829889524962640001Checkpoint-14000:https://x.com/kadirnar_ai/status/1829989622878744711Checkpoint (16000-18000):https://x.com/kadirnar_ai/status/1830179551407665654Dataset: kadirnar/fluxdev_controlnet_16kGPU: 1xA100(80GB)GPU Hours: 65 1 reply Β· π 8 8 β€οΈ 7 7 π₯ 4 4 π 4 4 π€― 1 1 + Reply
Consent in Crisis: The Rapid Decline of the AI Data Commons Paper β’ 2407.14933 β’ Published Jul 20, 2024 β’ 12
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions Paper β’ 2406.15877 β’ Published Jun 22, 2024 β’ 48
view post Post 4445 Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Demo(Zero A100): kadirnar/Stable-Diffusion-3Paper: https://arxiv.org/pdf/2403.03206Model Page: stabilityai/stable-diffusion-3-mediumThanks β€οΈ @dn6 @sayakpaul π 11 11 π 2 2 π€― 2 2 + Reply
view post Post 3941 Fast Tachyon SDXL Demo:Demo(Zero A100): kadirnar/BlackHole-LightningModel Page: https://civitai.com/models/414108/black-hole π₯ 9 9 π 1 1 π 1 1 β€οΈ 1 1 + Reply
view post Post 1920 BLACK HOLE SDXL Lightning:Prompt: a photo of a baby dragonSteps: 4 π 4 4 β€οΈ 2 2 + Reply
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order Paper β’ 2404.00399 β’ Published Mar 30, 2024 β’ 43
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning Paper β’ 2402.06619 β’ Published Feb 9, 2024 β’ 57
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing Paper β’ 2206.15076 β’ Published Jun 30, 2022 β’ 5
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model Paper β’ 2211.05100 β’ Published Nov 9, 2022 β’ 32
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset Paper β’ 2303.03915 β’ Published Mar 7, 2023 β’ 7
Running 10 10 Making Demos Leaderboard π Display leaderboard for machine learning demo submissions