view post Post 5080 Researchers developed Sonic AI enabling precise facial animation from speech cues ๐ง Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis See translation 1 reply ยท ๐ 8 8 ๐ฅ 6 6 ๐ 2 2 ๐ง 1 1 + Reply
view post Post 4209 I created my own AI image and video from scratch using the fal.ai platform ๐ซWorkflow: Flux Lora Training + Upscale + Kling AI(1.6) See translation 6 replies ยท ๐ฅ 7 7 ๐ 3 3 ๐ 3 3 + Reply
view post Post 4492 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 ยท ๐ 8 8 โค๏ธ 7 7 ๐ฅ 4 4 ๐ 4 4 ๐คฏ 1 1 + Reply
view post Post 4444 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 โค๏ธ @dn6 @sayakpaul ๐ 11 11 ๐ 2 2 ๐คฏ 2 2 + Reply
view post Post 3940 Fast Tachyon SDXL Demo:Demo(Zero A100): kadirnar/BlackHole-LightningModel Page: https://civitai.com/models/414108/black-hole ๐ฅ 9 9 ๐ 1 1 ๐ 1 1 โค๏ธ 1 1 + Reply
view post Post 1919 BLACK HOLE SDXL Lightning:Prompt: a photo of a baby dragonSteps: 4 ๐ 4 4 โค๏ธ 2 2 + Reply