Krea 2 Identity Edit

#v1.2 — new things

In the model:

• Better likeness

• Character sheets — use and creation

• Head/face swap (+ eye/person replace) — thanks to stablellama

• Outpainting

• Inpainting

• Try-on

• Better person removal

• Higher fidelity + a real high-res pass

In the nodes:

• ref_boost — reference-fidelity dial ← don't miss this one, try between 2 and 6

• Fixed blurry images / fit geometry (also removes the old "match the aspect ratio" requirement)

**Settings:** Turbo, 8–12 steps (8 = composition, 12 = face detail, ~10 balanced), CFG 1.0, LoRA strength 1.0. Removals/deletions: Two-ref edits: **scene = image 1, person = image 2.**

Requires the [ComfyUI-Krea2Edit nodes](https://github.com/lbouaraba/comfyui-krea2edit) — see [CHANGELOG](https://github.com/lbouaraba/comfyui-krea2edit/blob/main/CHANGELOG.md).

Instruction-based, identity-preserving image editing for Krea 2 (12.9B single-stream MMDiT). Give it an image and a plain-language instruction; it edits while preserving what you didn't ask to change — including the person.

An unofficial community fine-tune of Krea 2 Raw. Not an official Krea product; not affiliated with or endorsed by Krea.ai, Inc.

Requires the ComfyUI-Krea2Edit node pack — the LoRA is trained with dual conditioning (in-context VAE tokens + image-grounded Qwen3-VL encoding) that stock nodes don't provide. Two ready-made workflows ship with it.

What it does

• Person re-staging with likeness: "create a photo of this person at a night market" — same face, same outfit down to individual moles and marks, fully relit to the new scene. New camera angles and poses included.

• Local edits: recolor, add/remove/replace objects, attribute and outfit changes, with near-pixel preservation of the rest of the frame.

• Replace-with-reference: "replace the woman with a big orangutan" — the replace verb is trained, locality holds.

• Full-image restyles: global style with preserved composition.

• Two-input edits (experimental): scene + person as separate references. Outfits and placement work well; see limitations for faces.

• Composes with your LoRAs: character/body/style LoRAs stack on top and steer the prior — something closed editors structurally can't offer.

Recommended settings

Task type Model Steps CFG Most edits (add, recolor, restyle, re-stage) Turbo 8 1.0 Removals / large deletions Raw 20 3.0

• Match the output aspect ratio to the source image. Training pairs are same-size; AR mismatch degrades preservation (edits may apply to only part of the frame).

• Generate at ≤2MP. Above that, source content can bleed or subjects duplicate (training was 768/1024-class).

• grounding_px is a real dial (trained range 512–1536): lower values = stronger edit adherence and more uniform scene changes; higher values = stronger identity/likeness. 768 is a balanced default; try 1024+ for people.

• At CFG > 1, ground the negative too (empty prompt + same image).

• LoRA strength 1.0.

Known limitations (honest list)

• Likeness is texture-faithful, proportion-conservative. Moles, skin character, hair, and lighting adapt beautifully; strongly distinctive facial geometry (unusual nose, eye spacing, face length) regresses toward typical proportions. People whose identity lives in texture and structure transfer best; geometry-defined faces read as a "close relative."

• Two-person inputs keep outfits distinct but faces drift toward each other. Workaround that works today: chain single-ref inserts (place person A, then a second edit pass adding person B from their reference).

• Removal works but is not yet reliable — always use the Raw/CFG 3 recipe; expect occasional re-renders instead of deletions.

• Outfit swaps are hit-or-miss — changing what a person wears sometimes works cleanly and sometimes doesn't apply; reroll or rephrase.

• Local edits aren't always perfectly local — add/remove/replace operations can sometimes alter other parts of the frame or shift the overall color grade. If preservation matters, compare against the source and reroll.

• Highly unusual visual content (extravagant hairstyles, extreme body types) can drift toward the base prior — a subject LoRA stacked on top fixes this.

License

The LoRA weights are a Derivative Model of Krea 2 and are distributed under the Krea 2 Community License Agreement (see also NOTICE). Key points for users: commercial use is permitted under the license's revenue threshold (§2.3, currently <$1M/yr — above that, contact Krea for an enterprise license); deployments must implement reasonable content moderation (§4.2); AI disclosure obligations apply where required (§4.3). This repository modifies the Krea Model as permitted by §3; it is not endorsed by Krea.

Research/portfolio release by a self-funded hobbyist.

Showcase

All reference people below are themselves AI-generated — no real likenesses. Prompts are embedded in each image.