Liming Jiang

Research Lead, Generative Foundation Models @ Cantina. Ex. Staff Research Scientist (Tech Lead) @ ByteDance / TikTok, USA. Ph.D. @ MMLab@NTU.

[Xingang Pan @XingangP]

Introducing StoryMem — a memory-augmented framework for multi-shot long video storytelling.

StoryMem carefully injects compact memory into the generation process with minimal overhead, enabling:
• Cross-shot consistency
• Smooth transitions
• Narrative coherence across minutes-long videos

Awesome work by Kaiwen @sze68zkw

Project: https://t.co/NcTtVGCxWM
arXiv: https://t.co/Y3oObPlIjn
Code: https://t.co/OeHs5ltmHL

[Gorden Sun @Gorden_Sun]

StoryMem：生成多镜头长视频
将单镜头的AI视频模型（Wan2.2），增强为多镜头的视频模型，能生成镜头切换的长视频，类似Sora2。
Github：https://t.co/BMeEWOb9RO
模型：https://t.co/DCwBTaEs0P

[Wildminder @wildmindai]

StoryMem from ByteDance: A shot-by-shot long video generator;
- coherence + dynamic memory;
- Wan2.2-I2V + LoRAs;
nice cross-shot consistency (0.5065).
Now we can make long vids with frame-to-frame consistency and proper scene cuts.
https://t.co/Y8Qn5YDOKa

[AK @_akhaliq]

StoryMem

Multi-shot Long Video Storytelling with Memory
https://t.co/8jCJ4XZYzr

[Liming Jiang @SoraEndless]

InfiniteYou has been selected as an ICCV 2025 Highlight presentation! :-)

[Liming Jiang @SoraEndless]

🎉 Thrilled that our paper InfiniteYou (InfU) (https://t.co/xr7VrAfZGc) is accepted to #ICCV2025!
📸 Generate infinite, high-fidelity, identity-preserved photos of you with DiTs like FLUX.
Check out our paper, website, code, model, ComfyUI node, and demo—all released. Enjoy!

[AK @_akhaliq]

ByteDance just announced InfiniteYou available on Hugging Face

Flexible Photo Recrafting While Preserving Your Identity

[Yuxin Jiang @JYuxinn]

🚀A new way to use diffusion models for style transfer!

Style Matching Score (SMS) is accepted to #ICCV2025🌺
We reframe image stylization as a style distribution matching problem.

-Paper: https://t.co/3Aj1IMcijN
-Code: https://t.co/CXi7sc1iPx
-Project: https://t.co/l0m5mnsd2v

[Liming Jiang @SoraEndless]

Paper: https://t.co/nhfhPu63d3
Project Page: https://t.co/xr7VrAfZGc
Code: https://t.co/GlxkDfxJpD
Model: https://t.co/tWCGfsbk1m
ComfyUI Node: https://t.co/iJ17I7B4g9
Demo: https://t.co/EA6dhL13Co

[Liming Jiang @SoraEndless]

The official ComfyUI node of InfiniteYou is also available. Please feel free to try! https://t.co/xjUYpPBmSZ

[Liming Jiang @SoraEndless]

🚀 Introducing InfiniteYou (InfU) (https://t.co/XPqLa1Sc6k) for flexible, high-fidelity identity-preserved image generation!

📸 Create infinite photographs of You with Diffusion Transformers (DiTs) like FLUX.

Check out our paper, web, code, model, and demo—all released. Enjoy!

[Liming Jiang @SoraEndless]

@MasivasArt Thanks a lot for your interest. We are planning it. We also welcome community contributions.

[Liming Jiang @SoraEndless]

🚀 Introducing InfiniteYou (InfU) (https://t.co/XPqLa1Sc6k) for flexible, high-fidelity identity-preserved image generation!

📸 Create infinite photographs of You with Diffusion Transformers (DiTs) like FLUX.

Check out our paper, web, code, model, and demo—all released. Enjoy!

[AK @_akhaliq]

ByteDance just announced InfiniteYou available on Hugging Face

Flexible Photo Recrafting While Preserving Your Identity

[Liming Jiang @SoraEndless]

Project Page: https://t.co/xr7VrAfZGc
Paper: https://t.co/nhfhPu63d3
Code: https://t.co/GlxkDfxJpD
Model: https://t.co/tWCGfsbk1m
Demo: https://t.co/EA6dhL13Co

[AK @_akhaliq]

Bytedance just released InfiniteYou app on Hugging Face

Flexible Photo Recrafting While Preserving Your Identity

[Liming Jiang @SoraEndless]

@myserver368 @_akhaliq FYI. Demo is now available :-)

[Liming Jiang @SoraEndless]

@myserver368 @_akhaliq We are trying to fix some demo issues. Will make the demo available and announce it soon.