Join my discord for access to Version 5: https://discord.gg/8wMr2mmaRF

Follow me on HuggingFace for all of my other releases that I cannot post here:

https://huggingface.co/obsxrver/

Update: I2-4 Public Release

I2-4 is the best freely available blink LoRA today. You can download and run it for free now.

No GPU? No Problem

Run ComfyUI on a cloud GPU using Vast.AI with this template https://cloud.vast.ai/?ref_id=208628&creator_id=208628&name=ComfyUI%20-%20Wan%202.2%20LoRA%20demo

WORKFLOW:

Download the workflow file https://huggingface.co/obsxrver/wan2.2-i2v-/resolve/main/config.json?download=true and drag into ComfyUI.

SageAttention:

The Vast.AI
template already provisions the instance, downloading all necessary
LoRA Files and installing SageAttention. However, if running locally,
you will need to install SageAttention to run the workflow:

``` pip install sageattention ```

Technical Explanation

Blink
introduces a novel training methodology for Image-to-Video (I2V)
diffusion transformers, termed Identity Invariant Action Mapping (IIAM).
This technique addresses the persistent challenge of identity drift and
hallucination in generative video by decoupling subject identity from
temporal action dynamics.

Traditional I2V training often results
in the model creating a smooth, continuous video, Blink teaches the
model to perform a hard-cut transition, switching to a completely new
scene, while preserving the and identity characteristics of the
input image. We achieve this by utilizing a specific data preprocessing
strategy:

1. Temporal Splicing: Training data consists of a 0.3-second static frame (the "before" image of the subject. Derived from the video using Qwen-Image-Edit) prepended to a 4.7-second action sequence
(the "after". Whatever you are training the LoRA to do). This "jumpcut"
forces the model to attend to the initial static latents as the ground
truth for identity.

2. Identity-Agnostic & Discontinuity-Forcing Captioning:

Template: "a [man|woman], jumpcut, after the transition, [he|she] is
(any change in appearance), [he|she] is (the action happening in the
"after" sequence)"

By any uniquely identifying
descriptors (e.g., hair color, structure, clothing), using only
generic identity references ("man", "woman", "he", "she"), the model is
forced to map the learned motion vectors and physics simulations
directly onto the visual topology provided in the initial frame. The
model learns to bind the discontinuous transition - the "blink" - to the
"jumpcut, after the transition" tokens.

Future Applications:

The
IIAM/Blink framework is content-agnostic and can be applied to any set
of action clips to create modular, "plug-and-play" motion LoRAs for
generative video workflows.

Description

FAQ

Comments (7)

boobkake222026년 5월 14일· 19 reactionsCivitAI

Here before the delete.

UrdNine2026년 5월 14일CivitAI

Finally!!!!!!!!!!!!!!!!

fronyax2026년 5월 14일CivitAI

This and the latest from igoon's are superb

Keroro_Gunso2026년 5월 14일· 1 reaction

Where to find

Jellai2026년 5월 14일

Latest? I just see stuff that's at least 3 months old on huggingface. Is that what you mean?

fronyax2026년 5월 14일

@Jellai
I subbed to him. Choking is the latest one, it was released a
couple of days ago. 3 months? He released a lot since then.

crafted1012026년 5월 14일

@fronyax link ?