Все модели
Полный список отсортирован по популярности на Replicate.
A diffusion model that changes an input image according to provided prompt
DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation
prompt strength: 1, guidance_scale 3:50, lora_bla_bla: 0.92
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Ultra-fast image generation model optimized for creating high-quality avatars.
Use DANIELBULL23 to trigger
The Thoth LoRA. The most occult AI fine-tune in existence. Be careful, you might see through the veil. :3
Let Vision Language Models Reason Step-by-Step
Playground v2.0: A diffusion-based text-to-image generation model trained from scratch by the research team at Playground
An experimental model for testing out different failure modes