conradlocke/krea2-identity-edit · Hugging Face

Source: https://huggingface.co/conradlocke/krea2-identity-edit

https://huggingface.co/conradlocke/krea2-identity-edit#krea-2-identity-editKrea 2 Identity Edit

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 ofKrea 2 Raw. Not an official Krea product; not affiliated with or endorsed by Krea.ai, Inc.

Requires theComfyUI-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.

https://huggingface.co/conradlocke/krea2-identity-edit#what-it-doesWhat 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.

https://huggingface.co/conradlocke/krea2-identity-edit#recommended-settingsRecommended settings

Task typeModelStepsCFGMost edits (add, recolor, restyle, re-stage)Turbo81.0Removals / large deletionsRaw203.0

• **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\_pxis 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.

https://huggingface.co/conradlocke/krea2-identity-edit#known-limitations-honest-listKnown limitations (honest list)

• **Likeness is texture-faithful, proportion-conservative.**Moles, skin character, hair, and lighting adapt beautifully; strongly distinctive facialgeometry(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.

https://huggingface.co/conradlocke/krea2-identity-edit#licenseLicense

The LoRA weights are aDerivative Model of Krea 2and are distributed under the**Krea 2 Community License Agreement**(see alsoNOTICE). 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.

https://huggingface.co/conradlocke/krea2-identity-edit#showcaseShowcase

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