### 💬 Questions or setup issues?Join the <a target="_blank" rel="ugc" href="https://discord.gg/ePYDwxzhc">[Artfat AI Discord]</a>. I help with installation, workflows and prompting there, and it's where the community hangs out.Solo project, so the free stuff stays free ☕ Want new models early plus a Discord role? Skool link <a target="_blank" rel="ugc" href="https://www.skool.com/artfat-ai-6792">Artfat AI</a>---&gt; ## ⚡ REWORKED FOR my merge checkpoint model <a target="_blank" rel="ugc" href="https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint">SELFORA v.2</a>&gt; This v1.1 is fully re-tuned around the new Selfora v.2 checkpoint — samplers, upscale, detailers and presets all adapted for it.&gt; 👉 [Get Selfora v.2 here](<a target="_blank" rel="ugc" href="https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint)**">https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint)</a>---## Selfism AIO Krea 2 v.1.1 — the workflow behind SelforaMy signature preset-driven pipeline for realistic amateur / phone-photo generation. Tuned around Selfora v.2, but works with any Krea 2 model. The AIO version adds Edit, ControlNet and Colorgrade modes on top of the standard generation.### 🆕 New in v1.1- Reworked for <a target="_blank" rel="ugc" href="https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint">Selfora v.2</a> — the whole pipeline (samplers, upscale, detailers, presets) is re-tuned around the new <a target="_blank" rel="ugc" href="https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint?modelVersionId=3207355">Selfora_v2_Krea 2 (realistic amateur checkpoint) - int8 | Krea 2 Checkpoint | Civitai</a>- Optional second pass — after the mid upscale you get a preview; a lot of the time it's already clean and you can stop there. Second pass OFF = rawer / more real, ON = extra polish for skin and close-ups. Your call per shot.- Pixel upscale between passes (4xPurePhoto-RealPLSKR) on a simple ON/OFF toggle — clean hi-res with no mesh artifacts. Three previews (base → upscaled → final) so you see every stage.- Separate eye + hair detailers — clean, open eyes and natural hair even on full-body or far-away shots, not just close-ups.- Projector Tuner — push facial expression and prompt-following without adding any LoRA. Ships neutral; crank it for more emotion on portraits.## What's inside- Artfat LLM Prompter — image/text → prompt, on-device (no API). Dozens of ready selfie/amateur style presets.- Face Style Preset — one-click phone-camera face presets for FaceDetailer (skin, grain, the "real" look).- 2-pass generation with an optional, toggleable pixel upscale between passes (~1.5x–2x), plus a pre-pass-2 preview so you decide when it's done.- Eye + hair detailers and a skin-contrast pass for clean, real-looking faces at any distance.- Projector Tuner — expression / prompt-following control, no extra LoRA.- Edit Mode — Krea 2 Identity Edit: restage, change clothes, outfit transfer, masked local edits.- ControlNet Mode — reproduce the pose &amp; composition of a reference image.- Colorgrade (LUT) — final-look grading, film grain, and a standalone image editor.- Resolution reference table baked in — pick a ratio, go.## How to use (standard generation)1. Load Selfora v.2 (or any Krea 2 checkpoint).2. Pick a preset in the LLM Prompter, drop a reference image (optional).3. Choose resolution from the table → Run.4. Check the previews — stop after the upscale if it already looks great, or let the second pass polish it.No trigger words. Sampler + settings pre-dialed.💡 Quick tips: keep the shorter side around 1024 for best results. For open eyes, write "smiling softly, relaxed wide-open eyes looking at the camera" — a hard laugh tends to squint the eyes. Full setup + download links are in the "Model Links" note inside the workflow.---✏️ EDIT MODE — Krea 2 Identity EditInstruction-based editing that keeps the subject's identity. Runs on the Turbo checkpoint.LoRAskrea2_identity_edit_v1_2 — general edit LoRA, handles all operations below.krea_outfittransfer — dedicated outfit / clothing swap; trigger "transfer the outfit".What it can doRe-stage a person — keep the face, change scene/light: "Create a photo of this person at a night market"Change clothing — "Change her black dress to a red dress"Add / remove / replace — "Remove the necklace" / "Replace the woman with a big orangutan"Outfit Transfer — apply an outfit from a reference: "replace the clothes of the woman in the image 1, transfer the outfit from the image 2"Restyle whole image — "make it look like 90s film photography"2-image compose — scene = Image 1, person = Image 2 (order is fixed)Turn Edit Mode ON (Fast Groups Bypasser)Load VAE for Edit Mode → krea2RealVae_v10 or Wan2.1_VAE_upscale2x_imageonly_real_v1 (the latter also gives a ×2 upscale).Enable reference image 1 (and image 2 if used).ENABLE Krea2 identity edit.DISABLE the first sampler ClownShark — required.Two references → enable both ref toggles + Enable edit Image 2.Mask edit (first image only): right-click the reference → Open in Mask Editor → paint the area → Save → ENABLE Enable Mask edit.💡 Stronger face identity: in the Krea2 identity edit subgraph set ref_boost = 4 (locks reference face / hair / clothes). Lower it if a bigger edit isn't "taking".Settings: Turbo — 8–12 steps · CFG 1.0 · LoRA 1.0 · image ≤ 2 MP, dimensions divisible by 8.Prompting: plain natural-language instructions, no trigger word — except Outfit Transfer.---🎯 CONTROLNET MODE — Krea 2 (Depth)Reproduce the pose &amp; composition of a reference image via a Control-LoRA (it patches the model, not a classic ControlNet). ⚠️ Output is a similar image built from the LLM's reading of the input — not an exact copy.How to useEnable Enable Image 1 → load the image whose pose / composition you want to reproduce.Flip ON CONTROL NET (FIRST REF IMAGE ON) → true — routes the source latent into the ControlNet Group. (required)In Fast Groups Bypasser (rgthree) enable ControlNet Group + LLM PROMPTER.Pick the LLM preset: ControlNet_Edit_Mode or K1_Krea2_HighDetailed.Everything else — as in standard generation.Panel controls: strength Lora — structure hold (default 0.90; lower = looser, higher = stricter) · resolution limit — max side (default 1920).Depth is the released control type (canny / pose / normal need a matching Control-LoRA).---🎨 COLORGRADE (LUT) — final look &amp; grainGrades the final image and gives it that amateur-photo feel.LUT filters — apply .cube LUT files. Drop your own into ComfyUI/custom_nodes/ComfyUI-OlmLUT/luts/ and they appear in the list.Tone controls — temperature, hue, brightness, contrast and more, for fine final-look tuning.Digital grain — grain amount, grain size, color amount — adds realistic sensor noise so renders read as phone photos, not CG.Standalone editor — you can grade any image from your PC: switch the slider to 2, upload it via upload image for edit, and disable the SAMPLING module in Fast Groups Bypasser.A|B compare — set the selector to 1 or 2 depending on which photo you're processing, so the before/after view shows correctly.---👉 Model: [Selfora v.2 — (<a target="_blank" rel="ugc" href="https://civarchive.com/models/2841090/selforav2krea-2-realistic-amateur-checkpoint?modelVersionId=3207355">Selfora_v2_Krea 2 (realistic amateur checkpoint) - int8 | Krea 2 Checkpoint | Civitai</a>)Required custom nodesSee the "Model Links" note inside the workflow — everything is listed with direct download links. Install missing ones via ComfyUI-Manager.SupportSolo project, so the free stuff stays free ☕ Want new models early plus a Discord role? Skool link <a target="_blank" rel="ugc" href="https://www.skool.com/artfat-ai-6792">Artfat AI</a>

Selfism AIO Krea 2 v.1.1  | LLM PROMPTER | KREA2 EDIT | CONTROLNET | FACESTYLE PRESETS | LUT`s | COLORGRADE | MORE 50 PROMT PRESETS

🆕 New in v1.1<ul><li>Reworked for Selfora v.2 — the whole pipeline (samplers, upscale, detailers, presets) is re-tuned around the new <a target="_blank" rel="ugc" href="https://civitai.red/models/2841090/selforav2krea-2-realistic-amateur-checkpoint">Selfora v.2 checkpoint</a>.</li><li>Optional second pass — after the mid upscale you get a preview; a lot of the time it's already clean and you can stop there. Second pass OFF = rawer / more real, ON = extra polish for skin and close-ups. Your call per shot.</li><li>Pixel upscale between passes (4xPurePhoto-RealPLSKR) on a simple ON/OFF toggle — clean hi-res with no mesh artifacts. Three previews (base → upscaled → final) so you see every stage.</li><li>Separate eye + hair detailers — clean, open eyes and natural hair even on full-body or far-away shots, not just close-ups.</li><li>Projector Tuner — push facial expression and prompt-following without adding any LoRA. Ships neutral; crank it for more emotion on portraits.</li></ul>

Files with SHA256: cb15e5331d821b8316135b475e57101255f445fb3de25e38839eac185faba8e2