<h1 id="influencergram-or-moss-image-lora">InfluencerGram | MOSS-Image LoRA</h1>Sharper, more authentic Instagram-style photos from MOSS-Image.MOSS is already really good at making Instagram photos. InfluencerGram isn't meant to replace it, just to push it further. It focuses on three things:<ul><li>Sharpness. Clean edges, detailed faces and real per-pixel detail at full resolution. It works especially well with the 8-step DMD2 turbo LoRA, which on its own tends to look like an upscaled low-res image. With InfluencerGram the turbo output comes out crisp.</li><li>Authenticity. The look of real phone photos: mirror selfies, flash, casual framing, everyday rooms. Results get very close to real Instagram posts, further than the base model, KroMoss or other LoRAs I've tried.</li><li>Body proportions and poses MOSS doesn't know well. Petite and slim bodies, thigh gap, camel toe, and more expressive, dynamic body positions.</li></ul>It's not perfect, and I'll keep iterating on it as time goes on, especially if there's enough interest.<h2 id="how-to-use">How to use</h2><ul><li>Trigger: start your prompt with <code>influencergram photo.</code></li></ul><ul><li>Prompt style: write a full natural-language description after the trigger. MOSS was trained on long captions, and so was this LoRA, so describe the body, outfit, pose, camera angle, setting and lighting.</li></ul><ul><li>Strength: 1.0. Anything from 0.8 to 1.4 makes no noticeable difference, so there's no need to fine-tune it.</li></ul><ul><li>Base model: works on MOSS-Image Base and SFT or Kromoss.</li><li>Turbo: stacks well with the 8-step DMD2 LoRA (both at 1.0, 8 steps, CFG 1).</li><li>Without turbo: CFG around 3, 30 to 50 steps. Adding <code>watermark, username, text overlay</code> to the negative prompt helps. (Negative prompts do nothing at CFG 1, so this tip doesn't apply to turbo.)</li></ul><h2 id="training">Training</h2><ul><li>Personal Dataset: about 1,250 images, carefully curated by hand: duplicates and near-duplicates removed, and anything made with AI excluded.</li><li> Source: Instagram and OnlyFans. Both SFW and NSFW. All subjects are adults.</li><li>Captions: long, detailed natural-language captions written by Qwen3.5-9B. They describe body shape, pose, outfit, camera and setting, and quote any watermarks or text overlays, so those stay out of your images unless you prompt for them. "A watermark in the bottom right corner reads "OnlyFans.com/####"</li><li>Settings: trained on MOSS-Image Base with kohya sd-scripts. Rank 32 / alpha 32, AdamW, learning rate 1e-4, 1024 px buckets, 3,750 steps.</li></ul>## Notes<ul><li>Trained on women. Men and groups weren't a focus and are not included.</li><li>Watermarks and usernames appeared in a good share of the source photos. They were captioned so the LoRA treats them as separate from the look, but a faint corner text can occasionally slip through.</li></ul>

Files with SHA256: 3770cd5ff1d1e8b4a64c7dc94935d8b105c53aaf39c8b6f608b0a5bdd519e62b