https://youtu.be/CU1UKxjWBRo 
 
This workflow is the masked single-image editing version for Krea 2 Identity Edit v1.2. It is designed for creators who want to change a specific part of one image while keeping the rest of the frame as stable as possible. Instead of asking the model to reinterpret the entire picture, you mark the target region and let the workflow focus the edit there. That makes it useful for outfit replacement, local retouching, object changes, hair or accessory edits, background patching, and other cases where a normal image-to-image pass would drift too far. 
 
The inspected graph uses `krea2_turbo_fp8_scaled.safetensors` as the active UNET route, `qwen3vl_4b_fp8_scaled.safetensors` as the Krea2 CLIP/text encoder, and `qwen_image_HDR_vae_fp32_comfy.safetensors` as the VAE. The important LoRA is `krea2_identity_edit_v1_2_fp16.safetensors`, enabled at strength 1.0. The graph exposes a 1536 x 1536 latent canvas and a 10-step KSampler using CFG 1 with euler/simple sampling. The output path reaches both preview and save nodes, so the workflow can be used for quick checking and final export. 
 
The value of this setup is not raw upscaling; it is controlled localized editing. Use the mask to tell the model where the change should happen, then keep the prompt focused on the replacement or correction you need. Because Krea 2 Identity Edit v1.2 is loaded as the active edit LoRA, this workflow is especially useful when you want the subject identity and global composition to remain recognizable while still making a visible local change. 
 
Main features: 
 
- Krea 2 Turbo FP8 active UNET path 
- Krea 2 Identity Edit v1.2 LoRA enabled at strength 1.0 
- Qwen3VL 4B FP8 Krea2 text encoder route 
- Qwen Image HDR VAE decode path 
- Mask-focused single-image editing setup 
- 1536 x 1536 latent canvas 
- 10-step euler/simple KSampler 
- CFG 1 low-guidance edit style 
- Preview and SaveImage output paths 
- Best for localized retouching and inpainting-style edits 
 
Suggested workflow: 
 
Load one source image, paint a clean mask over only the region you want to change, and write a direct prompt for that region. Keep the prompt short at first, then add details only if the edit is too vague. If the model changes areas outside the mask, reduce prompt ambiguity and make the mask tighter. If the edit does not appear strongly enough, expand the mask slightly or make the replacement instruction more explicit. 
 
RunningHub Workflow 
 
Try the workflow online right now - no installation required. 
Workflow: https://www.runninghub.ai/post/2079889918284877826?inviteCode=rh-v1111 
 
If the results meet your expectations, you can later deploy it locally for customization. 
 
Fan Benefits: Register to get 1000 points + daily login 100 points - enjoy 4090 performance and 48 GB super power! 
 
Bilibili Updates (Mainland China &amp; Asia-Pacific) 
 
If you are in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown. 
Bilibili Video: https://www.bilibili.com/video/BV1bJgy6eEei/ 
 
Support Me on Ko-fi 
 
If you find my content helpful and want to support future creations, you can buy me a coffee. 
Every bit of support helps me keep creating. 
Ko-fi: https://ko-fi.com/aiksk 
 
Business Contact 
 
For collaboration or inquiries, please contact aiksk95 on WeChat. 
 
打开下方链接即可在线体验，无需安装。 
工作流：https://www.runninghub.ai/post/2079889918284877826?inviteCode=rh-v1111 
 
如果觉得效果理想，也可以在本地进行自定义部署。 
 
粉丝福利：注册即送 1000 积分，每日登录 100 积分，畅玩 4090 体验 48G 超级性能。 
 
Bilibili 更新（中国大陆及亚太地区） 
 
如果你在中国大陆或南亚太地区，可以通过下方视频查看该工作流的实测效果与构思讲解。 
B站视频：https://www.bilibili.com/video/BV1bJgy6eEei/ 
 
本期 Krea 2 相关模型资源： 
https://pan.quark.cn/s/07bdc81784ce?pwd=FpDf#/list/share 
 
这些资源主要面向本地用户，方便进行创作与学习。

Krea2 Masked Single Image Edit

krea2MaskedSingle_v10.json

v1.0

<div data-youtube-video="https://youtu.be/CU1UKxjWBRo"><iframe src="https://www.youtube.com/embed/CU1UKxjWBRo" width="853" height="480" allowfullscreen></iframe></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2079889918284877826?inviteCode=rh-v1111
<h2>Krea 2 Identity Edit v1.2 - Single-Image Mask Editor</h2>
Purpose: the masked variant of the Krea 2 Identity Edit v1.2 graph. You supply one image plus a mask, and the instruction is applied only where the mask allows, which is how you edit one object (a product, a piece of clothing, a detail) without repainting the rest of the frame.
<h2>Graph (as saved)</h2>
22 nodes / 27 links. Groups: Mask.
<ul>
<li>UNETLoader: <code>krea2_turbo_fp8_scaled.safetensors</code>; LoRA: <code>krea2_identity_edit_v1_2_fp16.safetensors</code> at strength 1.</li>
<li>CLIPLoader: <code>qwen3vl_4b_fp8_scaled.safetensors</code>, type <code>krea2</code>; VAE: <code>qwen_image_HDR_vae_fp32_comfy.safetensors</code>.</li>
<li>KSampler: 10 steps, CFG 1, <code>euler</code>, <code>simple</code>, denoise 1.</li>
<li>Krea2EditModelPatch: ref_boost 3, single-image mode, fit.</li>
<li>GrowMask: expand 6, taper on - the saved mask is grown before it gates the edit.</li>
<li>Krea2EditGroundedEncode: the example instruction adds thin black cat-eye sunglasses and explicitly asks to preserve face, hairstyle, flower accessory, makeup, clothing, background and lighting (encode size 768).</li>
<li>SaveImage prefix <code>ComfyUI/Kera2Edit</code>.</li>
</ul>
<h2>How to use</h2>
Load the image and its mask, then write the change with an active verb ("add", "replace", "change", "make"). The grow setting is worth tuning per subject: too tight and the edit shows a seam, too wide and unrelated areas start changing. The example instruction is a good template for identity-preserving object edits because it names what must not change.
<h2>Limits and not-verified items</h2>
No inference was run for this listing: no speed, VRAM, mask-alignment or quality claim is made. The saved mask, image and instruction are the author's demo content, not evidence of an output. Mask behaviour depends on the exact node implementation and image; verify it on your own material. Weights, LoRA and input media are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: <a href="https://www.youtube.com/watch?v=CU1UKxjWBRo" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1bJgy6eEei" rel="ugc">Bilibili</a>. Workflows are supplied through AI-KSK; verify workflow, node, model, LoRA, source-image and cover rights separately. No blanket commercial or redistribution license is asserted.

Krea 2 Identity Edit v1.2 - Single-Image Mask Editor

<div data-youtube-video="https://youtu.be/CU1UKxjWBRo"></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2079889918284877826?inviteCode=rh-v1111
Krea 2 Identity Edit v1.2 - Single-Image Mask Editor
Purpose: the masked variant of the Krea 2 Identity Edit v1.2 graph. You supply one image plus a mask, and the instruction is applied only where the mask allows, which is how you edit one object (a product, a piece of clothing, a detail) without repainting the rest of the frame.
Graph (as saved)
22 nodes / 27 links. Groups: Mask.
<ul>
<li>UNETLoader: <code>krea2_turbo_fp8_scaled.safetensors</code>; LoRA: <code>krea2_identity_edit_v1_2_fp16.safetensors</code> at strength 1.</li>
<li>CLIPLoader: <code>qwen3vl_4b_fp8_scaled.safetensors</code>, type <code>krea2</code>; VAE: <code>qwen_image_HDR_vae_fp32_comfy.safetensors</code>.</li>
<li>KSampler: 10 steps, CFG 1, <code>euler</code>, <code>simple</code>, denoise 1.</li>
<li>Krea2EditModelPatch: ref_boost 3, single-image mode, fit.</li>
<li>GrowMask: expand 6, taper on - the saved mask is grown before it gates the edit.</li>
<li>Krea2EditGroundedEncode: the example instruction adds thin black cat-eye sunglasses and explicitly asks to preserve face, hairstyle, flower accessory, makeup, clothing, background and lighting (encode size 768).</li>
<li>SaveImage prefix <code>ComfyUI/Kera2Edit</code>.</li>
</ul>
How to use
Load the image and its mask, then write the change with an active verb ("add", "replace", "change", "make"). The grow setting is worth tuning per subject: too tight and the edit shows a seam, too wide and unrelated areas start changing. The example instruction is a good template for identity-preserving object edits because it names what must not change.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, mask-alignment or quality claim is made. The saved mask, image and instruction are the author's demo content, not evidence of an output. Mask behaviour depends on the exact node implementation and image; verify it on your own material. Weights, LoRA and input media are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: <a href="https://www.youtube.com/watch?v=CU1UKxjWBRo" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1bJgy6eEei" rel="ugc">Bilibili</a>. Workflows are supplied through AI-KSK; verify workflow, node, model, LoRA, source-image and cover rights separately. No blanket commercial or redistribution license is asserted.

Files with SHA256: e233e86b616f83af1d37fb0bf9ac0d8cd499edf91fce7f2b06e5a54bbd8f3b95