469 GB
174 files
Updated 5 months ago
Name
Size
comfy
.gitattributes1.52 kB
xet
1_Normx2.5.safetensors160 Bytes
xet
2_Strongx3_wl7.safetensors160 Bytes
xet
3_Strongx2.5.safetensors160 Bytes
xet
4_Normx4.0.safetensors160 Bytes
xet
5_Hybrid.safetensors160 Bytes
xet
Andrew-LayLay.safetensors457 MB
xet
BSS_AJlbTyIIIKu_Krea2.safetensors229 MB
xet
BetterAnimeStyle_Krea2_v1.safetensors229 MB
xet
BreastSlider-KREA2.safetensors10.1 MB
xet
CHANGELOG.md1.99 kB
xet
Casting-v3-rank32-krea2-lora-000003.safetensors469 MB
xet
Casting_v2_rank32.safetensors469 MB
xet
Detailer-KREA2.safetensors11.5 MB
xet
Flat_anime_Krea_@.safetensors229 MB
xet
Hogtied_Krea2_epoch_10.safetensors229 MB
xet
Huihui-Qwen3-VL-4B-Instruct-abliterated-fp8_scaled.safetensors5.24 GB
xet
Huihui-Qwen3-VL-4B-Instruct-abliterated.safetensors8.88 GB
xet
Huihui-Qwen3-VL-4B-Thinking-abliterated-fp8_scaled.safetensors5.24 GB
xet
Huihui-Qwen3-VL-4B-Thinking-abliterated.safetensors8.88 GB
xet
ImprovedEvilSmile_Krea2.safetensors229 MB
xet
ImprovedFear_Krea2.safetensors229 MB
xet
Incase_Krea_v2_epoch_10.safetensors229 MB
xet
K2_pillory_V1.safetensors229 MB
xet
KNPV3_1.safetensors229 MB
xet
KNPV4.1_pre.safetensors457 MB
xet
KNP_V2_copy_copy.safetensors229 MB
xet
Krea-2-Base-Q5_K_M.gguf8.87 GB
xet
Krea-2-Base-Q6_K.gguf10.6 GB
xet
Krea-2-Tini-Breasts.safetensors229 MB
xet
Krea-2-Turbo-Q4_K_M.gguf7.49 GB
xet
Krea-2-Turbo-Q5_K_M.gguf8.87 GB
xet
Krea-2-Turbo-Q5_K_S.gguf8.82 GB
xet
Krea-2-unlocked.safetensors48.4 MB
xet
Krea2-HD-vae.safetensors508 MB
xet
Krea2-Raw-int8-ConvRot.safetensors14.1 GB
xet
Krea2-TaylorSwift.safetensors229 MB
xet
Krea2-Turbo-int8-ConvRot.safetensors14.1 GB
xet
Krea2-realism-V2.safetensors1.56 GB
xet
Krea2_Cum_Facial_Cumshot_K2_epoch_14.safetensors229 MB
xet
Krea2_HMNSFW_AIO.safetensors229 MB
xet
Krea2_JanieshaWiggins_000002500.safetensors229 MB
xet
Krea2_Raw_convrot_int8mixed.safetensors12.9 GB
xet
Krea2_Turbo_convrot_int8mixed.safetensors12.9 GB
xet
Krea2__shealynnwatson.safetensors114 MB
xet
Krea_Breast_Implanter_v2.safetensors391 MB
xet
LICENSE14.6 kB
xet
LoRAKugisakiNobaraKrea2V1.safetensors229 MB
xet
Lotus_tied_-_zkrd.safetensors229 MB
xet
Marge-Simpson.safetensors229 MB
xet
MysticXXX_KREA2_v1.safetensors229 MB
xet
MysticXXX_KREA2_v2.safetensors229 MB
xet
MysticXXX_KREA2_v2_stripped.safetensors13.8 MB
xet
NOTICE313 Bytes
xet
Pole-Post-Tree-Bound.safetensors457 MB
xet
PornMaster_Detail_Slider_Krea2_V1_000000225.safetensors28.6 MB
xet
Qwen3-VL-4B-Instruct-Uncensored-FP8.safetensors5.68 GB
xet
Qwen3-VL-4B-Instruct-Unredacted-MAX.Q8_0.gguf4.28 GB
xet
Qwen3-VL-4B-Instruct-Unredacted-MAX.mmproj-f16.gguf836 MB
xet
Qwen3-VL-4B-Thinking-Unredacted-MAX.Q8_0.gguf4.28 GB
xet
Qwen3-VL-4B-Thinking-Unredacted-MAX.mmproj-f16.gguf836 MB
xet
README.md3.92 kB
xet
RLY-thot_shot-KREA2-annika-v1-trigger-rlyannika.safetensors229 MB
xet
RLY-thot_shot-KREA2-aspen-v11-trigger-rlyaspen.safetensors229 MB
xet
RLY-thot_shot-KREA2-christine-v1-trigger-rlychristine.safetensors229 MB
xet
RLY-thot_shot-KREA2-helena-v1-trigger-rlyhelena.safetensors229 MB
xet
RLY-thot_shot-KREA2-irena-v1.safetensors229 MB
xet
RLY-thot_shot-KREA2-marley-v1-trigger-rlymarley.safetensors229 MB
xet
RLY-thot_shot-KREA2-rayven-v1-trigger-rlyrayven.safetensors229 MB
xet
RLY-thot_shot-KREA2-skye-v1-trigger-rlyskye.safetensors229 MB
xet
RLY-thot_shot-KREA2-taryn-v1-trigger-rlytaryn.safetensors229 MB
xet
Raw-Projector-Scale.safetensors268 Bytes
xet
RebelReal.safetensors229 MB
xet
RedCraft-Red-Mix-Edition-NSFW.safetensors13.1 GB
xet
SummerVibesHM_krea2_epoch8.safetensors229 MB
xet
TheFutonEra-Krea2Raw_15k-17-5_EMA.safetensors229 MB
xet
TinyTitsV2.1_000001750.safetensors114 MB
xet
Turbo-Projector-Scale.safetensors268 Bytes
xet
Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors508 MB
xet
Wan2.1_VAE_upscale2x_imageonly_real_v1_bf16.safetensors254 MB
xet
Wan2_1_VAE_fp32.safetensors508 MB
xet
age_krea2_loraholic.safetensors7.2 MB
xet
ass_krea2_loraholic.safetensors14.3 MB
xet
bf95DarkbeastKreaTurbo8_v10.safetensors13.1 GB
xet
breast_size_krea2_loraholic.safetensors21.5 MB
xet
darkBeastINT8Convrot2_krea211INT8Convrot.safetensors14.1 GB
xet
darkBeastKrea2_darkBeastKREA2.safetensors12.8 GB
xet
fedor_bypass.safetensors1.04 kB
xet
femboy_krea2.safetensors229 MB
xet
frombelow-krea-turbo.safetensors229 MB
xet
k2_bp_v2.0.safetensors391 MB
xet
krea-2-turbo-int8-convrot-aggressive.safetensors13.8 GB
xet
krea2-masterpieces-v51.safetensors215 MB
xet
krea2Center_v05Fp8-Turbo.safetensors12.8 GB
xet
krea2Center_v05Int8.safetensors14.1 GB
xet
krea2Center_v11Int8Convrot.safetensors13.5 GB
xet
krea2RealVae_bf16.safetensors254 MB
xet
krea2RealVae_hdrVAE_mix_0.65_bf16.safetensors254 MB
xet
krea2RealVae_v10.safetensors508 MB
xet
README.md

Nynxz's Krea 2 Edit (NK2E)

A set of in-context LoRAs for Krea 2. The edit LoRAs take a source image and a text instruction (like "give her pink hair" or "add sunglasses") and edit the image. A separate canny control LoRA takes an edge map and generates an image that follows it.

Experimental and unofficial. Results are rough and inconsistent, and vary a lot by edit type. Not affiliated with or endorsed by Krea.

Demo

Try it in your browser — no install required — on the Hugging Face Space:

Open in Spaces

→ https://huggingface.co/spaces/nynxz/nk2e-krea2-editor

Links

Use (ComfyUI)

  1. Download a LoRA from comfy/v0.3/ (recommended) into your ComfyUI models/loras/.
  2. Install the node pack (link above) and load its example workflow.

Strength around 0.7 is a good start. The reference is the source image (or, for the canny LoRA, an edge map).

Versions

Version File Rank Steps Training data Notes
v0.3 comfy/v0.3/NK2E-v0.3.safetensors 64 24k v0.1 mix + UltraEdit + HQ-Edit (~72k pairs) recommended (newest)
v0.2 comfy/v0.2/NK2E-v0.2.safetensors 64 12k same ~72k mix continued from v0.1
v0.1 comfy/v0.1/NK2E-v0.1.safetensors 64 8k MagicBrush + OmniEdit + InstructPix2Pix (~37k) first release
canny v0.1 comfy/canny_v0.1/NK2E-canny-v0.1.safetensors 32 12k 8k COCO canny pairs control LoRA (see below)

See CHANGELOG.md for history.

What it does well (and not)

  • Good at: keeping identity and composition, localized edits (hair, accessories, objects), and global style or lighting changes.
  • Weaker at: recolouring a whole large region, and scene or structure changes (swapping a background, adding a person, re-posing).

It is not a mask or inpaint model; identity is preserved without a mask.

Canny control (experimental)

comfy/canny_v0.1/ is a separate control LoRA (ControlNet-style, in-context). Feed a canny edge map as the reference instead of a source image: structure comes from the edges, content from the text prompt. Same node setup as editing. It follows the outline but is softer than a pixel-locked ControlNet. Depth and pose are planned, same recipe.

Specialist LoRAs

comfy/loras/ holds narrow, single-purpose edit LoRAs trained on top of the generalist. Each responds to one trigger instruction rather than general edits, and loads with the same node setup. Because they are low-rank and concept-specific, they usually want a higher strength (start near 1.0).

Specialist File Base Trigger
Invisible Man comfy/loras/NK2E-InvisibleMan-v0.1.safetensors v0.3 make person invisible

See comfy/loras/README.md for details and triggers.

Training a specialist on top

comfy/ holds ComfyUI-format weights for inference; train/ holds native-format weights for training. Point the toolkit's base_lora at train/v0.3/NK2E-v0.3-train.safetensors (the latest generalist native) to train a narrow specialist on top — this is how the specialists in comfy/loras/ were made. See the training toolkit (link above).

License

Krea 2 Community License (see LICENSE and NOTICE); commercial use only under $1M/yr revenue. Not an official Krea project.

Total size
469 GB
Files
174
Last updated
Jul 7
Pre-warmed CDN
US EU US EU

Contributors