Four SCAIL 2 workflows focused on long-form reference editing — single and dual subjects, people and creatures.
| # | Workflow | Subjects |
|---|---|---|
| 1 | Single-reference edit, long video | 1 person |
| 2 | Single-creature long-video drive | 1 creature |
| 3 | Dual-reference edit, long video | 2 people |
| 4 | Dual-creature long-video drive | 2 creatures |
Reference editing works well on short clips and gets harder as length grows: the reference drifts,
the identity softens, and body proportions wander. These four graphs handle it by re-anchoring on
the reference at segment boundaries rather than conditioning once at the start.
Two people means two identities that must not merge. The dual-reference graphs keep separate
conditioning streams and only merge them at the sampler, which is why they survive longer than a
single combined prompt.
Workflow JSONs and covers: [https://huggingface.co/AI-KSK/ksk-video-261-comfyui-workflows](https://huggingface.co/AI-KSK/ksk-video-261-comfyui-workflows)
Video walkthrough (Chinese): [https://youtu.be/_LbRVl9hwnI](https://youtu.be/_LbRVl9hwnI)
Bilibili: [https://www.bilibili.com/video/BV1w2Ei6pEsJ/](https://www.bilibili.com/video/BV1w2Ei6pEsJ/)
source & further reading
dev.to — original article
LTX 2.3 MSR: Multi-Image Reference Video With Three-Stage Rendering
Are your model's probabilities calibrated? Expected calibration error in NumPy
Building a Security Reviewer Subagent