Melini AI

company

https://huggingface.co/

AI & ML interests

None defined yet.

MeliniAI's activity

kadirnar

posted an update about 17 hours ago

Post

456

Researchers developed Sonic AI enabling precise facial animation from speech cues 🎧 Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis

1 reply

·

kadirnar

posted an update 22 days ago

Post

2764

I created my own AI image and video from scratch using the fal.ai platform 💫

Workflow: Flux Lora Training + Upscale + Kling AI(1.6)

5 replies

·

kadirnar

posted an update 5 months ago

Post

4362

I am training a controlnet model for Flux. And some of my experiences:

Checkpoint-10000:

https://x.com/kadirnar_ai/status/1829831750471606668

Checkpoint-12000:

https://x.com/kadirnar_ai/status/1829889524962640001

Checkpoint-14000:

https://x.com/kadirnar_ai/status/1829989622878744711

Checkpoint (16000-18000):

https://x.com/kadirnar_ai/status/1830179551407665654

Dataset: kadirnar/fluxdev_controlnet_16k
GPU: 1xA100(80GB)
GPU Hours: 65

1 reply

·

kadirnar

posted an update 8 months ago

Post

4434

Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Demo(Zero A100): kadirnar/Stable-Diffusion-3

Paper: https://arxiv.org/pdf/2403.03206
Model Page: stabilityai/stable-diffusion-3-medium

Thanks ❤️ @dn6 @sayakpaul

kadirnar

posted an update 8 months ago

Post

3929

Fast Tachyon SDXL Demo:

Demo(Zero A100): kadirnar/BlackHole-Lightning

Model Page: https://civitai.com/models/414108/black-hole

kadirnar

posted an update 9 months ago

Post

1912

BLACK HOLE SDXL Lightning:

Prompt: a photo of a baby dragon
Steps: 4

kadirnar

posted an update 9 months ago

Post

1964

Midjourney + Custom SDXL-Lightning:

2 replies

·

kadirnar

posted an update 10 months ago

Post

2716

New SDXL model:

2 replies

·