<h1 id="selfora-realistic-amateur-checkpoint-(krea-2-turbo-uncensored)">Selfora — realistic amateur checkpoint (Krea 2 Turbo, uncensored)</h1>Selfora is a realism-first merge on Krea 2 Turbo built for one thing: believable amateur, shot-on-a-phone photos. Real skin with pores and texture, candid lighting, natural bodies — the kind of frame that looks like a selfie off someone's camera roll, not a glossy studio render. Ideal for AI-influencer / Instagram-style model content. Ideal for AI-influencer / Instagram-style model content. For that look with zero guesswork, pair it with my companion workflow — presets already tuned for this exact amateur-selfie output. → <a target="_blank" rel="ugc" href="https://civarchive.com/models/2776713/selfism-optimal-krea-2-v1-one-node-prompter-or-face-styler">Selfism Optimal Krea 2 v.1</a>. Every style LoRA is baked straight into the checkpoint — always on, nothing to stack or juggle. Fully uncensored, and just as strong on clean SFW. And it's Turbo, so you get there in a handful of steps.Selfora started as a personal project — built for my own use and convenience, to get this exact look without stacking LoRAs every time. It came out well enough that I'm sharing it. Huge thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/catlover1937">catlover1937</a> and to the author of the base model this checkpoint is built on, for kindly giving me permission to publish it.<h2 id="look-and-feel">Look &amp; feel</h2><ul><li>Amateur / smartphone photoreal — real skin, real light, no plastic</li><li>Candid "phone camera" energy, not editorial studio gloss</li><li>Made for AI Instagram models &amp; virtual influencers</li><li>Dialed-in out of the box — consistent without touching a single LoRA</li></ul><h2 id="recommended-settings-(krea-2-turbo)-2-pass-is-best">Recommended settings (Krea 2 Turbo) — 2-pass is best</h2>Two passes give the cleanest result: a base pass builds the image, a second partial-denoise pass refines skin and detail. Two variants — pick by whether you run RES4LYF. Both at CFG 1, 832×1216 (portrait) or 1024×1024.⭐ Variant 1 — my setup (RES4LYF / ClownsharKSampler)<ul><li>Pass 1 — base (ClownsharKSampler): sampler res_2s (exponential) · scheduler bong_tangent · 7 steps · eta 0.50 · bongmath on · denoise 1.0<ul><li>optional extras: ClownOptions Detail Boost (weight 1.10 · model · soft · eta 0.45 · start_step 2), Sigmas Rescale (start 1.0 → end 0.0)</li></ul></li><li>Pass 2 — refine (KSampler Advanced): euler · simple · 9 steps · start_at_step 4 → end 999 · add_noise on · return_with_leftover_noise off</li></ul>Variant 2 — portable 2-pass (plain KSampler Advanced, no extra nodes)<ul><li>Pass 1 — base: er_sde · simple · 8 steps · start 0 → end 8 · add_noise on · return_with_leftover_noise on</li><li>Pass 2 — refine: dpmpp_2m_sde · sgm_uniform · 9 steps · start_at_step 4 → end 999 · add_noise on · return_with_leftover_noise off</li></ul>Quick single-pass: er_sde · simple · 8 steps · CFG 1 (fast, still good).At CFG 1 the negative prompt does nothing — say what you do want, positively.<h2 id="prompting">Prompting</h2>No trigger words — the style lives in the weights. Just describe the scene.<h3 id="keywords-for-the-best-results-with-selfora">Keywords for the best results with Selfora</h3>The amateur / phone look is already baked in — you don't need any of these to get it. They just help you dial in a specific vibe (lighting, night, candid, camera) and get the most out of the model. Mix a couple from each group — you don't need all of them:<ul><li>Amateur / candid base: <code>amateur iphone selfie</code>, <code>candid facial expression</code>, <code>casual everyday appearance</code>, <code>unposed</code>, <code>friend-circle snapshot quality</code>, <code>instagram story upload quality</code></li><li>iPhone / camera look: <code>shot on iPhone</code>, <code>iPhone 15 Pro photo</code>, <code>warm iphone color science</code>, <code>soft computational HDR</code>, <code>soft phone bokeh</code>, <code>slight sensor grain</code>, front-camera selfie → <code>wide-angle front-camera distortion</code></li><li>Real skin (the realism boost): <code>natural unretouched skin texture</code>, <code>visible pores and freckles</code>, <code>minor blemishes</code>, <code>slight oily T-zone</code>, <code>natural makeup or bare face</code>, <code>realistic catchlights in eyes</code></li><li>Grittier / night (optional): <code>low light phone photo</code>, <code>ISO 6400 sensor noise</code>, <code>slight motion blur</code>, <code>handheld</code>, <code>warm tungsten light</code>, <code>night mode processing</code></li><li>Candid energy: <code>mid-laugh</code>, <code>genuine unposed expression</code>, <code>slightly tired eyes</code>, <code>casual</code></li></ul>Avoid (these push it toward studio/AI-gloss): <code>professional photography</code>, <code>studio lighting</code>, <code>DSLR</code>, <code>cinematic</code>, <code>retouched / airbrushed</code>, <code>8k</code>. At CFG 1 the negative prompt is ignored, so simply don't put these in the positive if you want the amateur look.💡 Don't want to type any of this? Use the Selfism_Krea2_optimal_v1 workflow. All of the above — the exact amateur styling, lighting, camera looks and candid vibes — is already dialed in as ready one-click presets. It's tuned specifically for Selfora, so for this exact look with zero prompt fiddling, running Selfora inside Selfism is the easiest, most reliable way.<h2 id="content">Content</h2>Uncensored, NSFW and SFW both. It favors realistic amateur NSFW, but clean portraits and everyday shots come out just as well.<h2 id="best-with-my-selfism_krea2_optimal_v1-workflow">Best with my Selfism_Krea2_optimal_v1 workflow</h2>Selfora runs best in my Selfism_Krea2_optimal_v1 workflow — it ships with lots of ready-made presets tuned for the selfie / amateur look and a full set of face-detailer presets, and the two sets are built to complement each other: the scene/selfie preset sets the shot, the face preset finishes the skin and detail — together they give a cohesive, consistent result. Powered by two custom nodes — Artfat LLM Prompter (image/text → prompt, on-device) and Artfat Face Preset (one-click phone-camera face presets). Load Selfora, pick your presets, shoot.👉 Workflow: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2776713/selfism-optimal-krea-2-v1-one-node-prompter-or-face-styler">Selfism Optimal Krea 2 v.1 ( ONE NODE PROMPTER | FACE STYLER )</a><h2 id="license-and-usage">License &amp; usage</h2>Personal, non-commercial use only. Don't sell the model or anything made with it, and don't use it commercially. This mirrors the terms of moody's base model — please respect them. Don't re-upload or pass this checkpoint off as your own.<h2 id="credits">Credits</h2>Built on <a target="_blank" rel="ugc" href="https://civarchive.com/models/2731187/moody-krea-2-mix-uncensored">moody Krea 2 Mix (uncensored)</a> by moody — massive thanks for the base and for the OK to share this merge.<h3 id="baked-loras-credits">Baked LoRAs — credits</h3>Full credit to the creators of the style LoRAs merged into this checkpoint (merged at my own balanced weights):<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2735553/krea-2-bloomgirls-ultrarealism">[Krea 2] BloomGirls UltraRealism</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2728365/krea2-realism-v1-or-v2">Krea2 Realism (V1/V2)</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2688234/realism-engine-ideogram-4-krea-2">Realism Engine (Ideogram 4 + Krea 2)</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1662740/lenovo-ultrareal">Lenovo UltraReal</a></li></ul>(Weights/balance are my own tuning and not published. If you made one of these and want the credit adjusted or removed, message me.)<h2 id="notes">Notes</h2>fp8, self-contained one-file checkpoint — just load and go.Planned for v2 (coming soon): an fp8_scaled build (quantized from the bf16 base for better quality) plus a full GGUF ladder for lower-VRAM setups. This v1 is the plain fp8 release.

Selfora Krea 2 (realistic amateur checkpoint)

Selfora — INT8 (RTX 30-series)INT8 (int8_tensorwise) quant of Selfora (Krea 2 Turbo). ~13.5 GB — about half of BF16. Built for RTX 30-series / Ampere, which has INT8 tensor cores (fp8 gives Ampere no speedup — INT8 does).⚠️ Requirements — read before downloading:ComfyUI ≥ 0.27 (native support). Load via UNETLoader — no custom nodes.If you get KeyError: 'int8_tensorwise' → your ComfyUI is too old, update it. (Not a broken file.)40/50-series users: use the fp8 / GGUF versions instead — INT8 gives you no benefit.Recommended (Krea 2 Turbo): sampler er_sde · scheduler simple · 8 steps · CFG 1.

Files with SHA256: 017e35ab9c1ffca1a33547efd3ee2c4690c0c3e786214aa153a818a997a8266d