# Sebastian + Jessica v2 — Dual Character LoRA (Microsoft Lens)Dual-character LoRA for [Microsoft Lens](<a target="_blank" rel="ugc" href="https://huggingface.co/microsoft/Lens-Base)**">https://huggingface.co/microsoft/Lens-Base)</a> — two recurring characters trained together in one adapter:- Sebastian — blonde man, long hair, Irish blue eyes, tuxedo- Jessica — redhead, long copper-red hair, Irish green eyes, purple dressTrained with [LoboForge LensTrainer](<a target="_blank" rel="ugc" href="https://github.com/LoboForge/LoboForge-LensTrainer)**">https://github.com/LoboForge/LoboForge-LensTrainer)</a> — a config-driven LoRA trainer built for Lens-Base (flow-match loss, ComfyUI export, 16–24GB VRAM presets).Community model — not affiliated with or endorsed by Microsoft.---## Links| | ||---|---|| Download (weights) | [Hugging Face — lens-lora-sebastian-jessica-v2](<a target="_blank" rel="ugc" href="https://huggingface.co/LoboForge/lens-lora-sebastian-jessica-v2">https://huggingface.co/LoboForge/lens-lora-sebastian-jessica-v2</a>) || Trainer (GitHub) | [LoboForge/LoboForge-LensTrainer](<a target="_blank" rel="ugc" href="https://github.com/LoboForge/LoboForge-LensTrainer">https://github.com/LoboForge/LoboForge-LensTrainer</a>) || Trainer docs (HF Space) | [LoboForge/LoboForge-LensTrainer](<a target="_blank" rel="ugc" href="https://huggingface.co/spaces/LoboForge/LoboForge-LensTrainer">https://huggingface.co/spaces/LoboForge/LoboForge-LensTrainer</a>) || LoboForge | [<a target="_blank" rel="ugc" href="http://LoboForge.com">LoboForge.com</a>](<a target="_blank" rel="ugc" href="https://LoboForge.com">https://LoboForge.com</a>) |---## Train your own Lens LoRAsIf you want to train subject or style LoRAs on Lens-Base yourself:- GitHub: <a target="_blank" rel="ugc" href="https://github.com/LoboForge/LoboForge-LensTrainer">https://github.com/LoboForge/LoboForge-LensTrainer</a>- Quickstart: <code>python train.py configs/train_lora_lens_base_24gb.yaml</code>- Docs Space: <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/LoboForge/LoboForge-LensTrainer">https://huggingface.co/spaces/LoboForge/LoboForge-LensTrainer</a>- More from LoboForge: <a target="_blank" rel="ugc" href="https://LoboForge.com">https://LoboForge.com</a>The trainer handles flow-match training, checkpoint resume, mid-run samples, and ComfyUI-compatible <code>diffusion_model.*</code> export.---## Training (this LoRA)| Field | Value ||-------|-------|| Base model | Lens / Lens-Base || Dataset | 24 image/caption pairs, 1024×1024 || Published checkpoint | 5000 steps || LoRA rank / alpha | 16 / 16 || Optimizer | AdamW 8-bit || VRAM preset | 24GB (offload + caches) |---## Prompt formatFull-sentence captions — no single trigger word. Describe both characters and the scene, similar to your training captions.Example:```Sebastian is a blonde man with long hair and irish blue eyes in a tuxedo. Jessica is a redhead woman with long copper colored red hair and irish green eyes in a purple dress named. They are standing together facing forward and laughing```---## Inference (Lens-Base)| Setting | Value ||---------|-------|| Steps | 50 || CFG | 5.0 || Resolution | 1024×1024 |ComfyUI: Load Lens-Base (or CivitAI Lens checkpoint) + this LoRA. Keys use the <code>diffusion_model.*</code> format from the trainer export.Lens-Turbo: 4 steps, CFG 1.0 — quality may differ from Lens-Base training.---## LicensePolyForm Noncommercial License 1.0.0 — non-commercial use only.Microsoft Lens base weights remain under their own license.

Micorsoft Lens - World FIRST Lens Lora

# Sebastian + Jessica v2 — Dual Character LoRA (Microsoft Lens)Dual-character LoRA for [Microsoft Lens](<a target="_blank" rel="ugc" href="https://huggingface.co/microsoft/Lens-Base)**">https://huggingface.co/microsoft/Lens-Base)</a> — two recurring characters trained together in one adapter:- Sebastian — blonde man, long hair, Irish blue eyes, tuxedo- Jessica — redhead, long copper-red hair, Irish green eyes, purple dressTrained with [LoboForge LensTrainer](<a target="_blank" rel="ugc" href="https://github.com/LoboForge/LoboForge-LensTrainer)**">https://github.com/LoboForge/LoboForge-LensTrainer)</a> — a config-driven LoRA trainer built for Lens-Base (flow-match loss, ComfyUI export, 16–24GB VRAM presets).Community model — not affiliated with or endorsed by Microsoft.---

Files with SHA256: a0189c143763b7b0c10b1e835c3b755715dee27198a409b74f444296ff218a5f