Skip to content

PaperCodex

Subscribe

Diffusion Transformer Control

ConsisID: Generate Identity-Preserving Videos from Text and a Single Image—No Fine-Tuning Required

ConsisID: Generate Identity-Preserving Videos from Text and a Single Image—No Fine-Tuning Required 790

Creating videos that faithfully preserve a person’s identity from just a text prompt and a reference image has long been…

01/13/2026Diffusion Transformer Control, Identity-preserving Video Generation, Text-to-video Synthesis
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex