Elusarca's Krea 2 Detail Enhancer (Edit LoRA): sharpen an existing image
Topic: Models
By Captain
Published 2026-09-29
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler
Steps
8
Guidance
1
Seed
566033944664300
Size
832x1216
Prompt
total darkness. hundreds of trains wrapping and twisting in rings, squares, spikes, waveforms, creating a four dimentional tunnel. strong long exposure trails. strong emission from the lights.
professional cinematic, a shot from a movie, faded film, film grain. ultra wide angle, fisheye. strchromatic aberration
Settings
Sampler
Euler
Steps
14
Guidance
1
Seed
2864161957
Size
2048x2048
Prompt
Close-up portrait of a woman looking directly at the camera. Her face and neck are mostly obscured by deep shadow. A single, narrow horizontal band of light cuts across her face, illuminating only her eyes and the bridge of his nose. He has a strong, defined jawline and short, textured hair. She is wearing a simple black shirt. The background is a plain, overcast grayish-blue sky. Dramatic, high-contrast lighting creates a moody, cinematic atmosphere.
(anime:-1.0),(cartoon:-1.0),(illustration:-1.0),visible pores,visible vellus hair,subsurface scattering,detailed skin texture,<lora:Krea2-realism-V1_copy:0.55>,<lora:5th training:0.65>,<lora:training_191944-20260708054915529:0.6>,<lora:cute_lass_krea2:0.55>,<lora:BeautyShots_krea2:0.25>,<lora:training_9619227-20260709100223878:0.2>,<lora:krea-detail-enhancer-exp-v2:0.15>,
Negative prompt
lowres,
reverentelusarca's experimental edit LoRA uses Ostris's Krea 2 edit method to enhance detail in an existing image. Learn the enhance this image trigger, the recommended prompt, limitations and ideas.
Overview
Elusarca's
Krea 2
Detail Enhancer
is an edit
LoRA
trained with Ostris's AI Toolkit method and custom
ComfyUI
node (ComfyUI-Krea2-Ostris-Edit), which lets Krea 2 edit images despite being a text-to-image model. It is experimental: Krea 2 is not an edit model, so expect less precision than dedicated editors, occasional changes to the image, slight lighting and color shifts and possible issues with horizontal aspect ratios.
Trigger: enhance this image. The author's prompt: Enhance this image to high resolution with rich fine details. Sharpen all textures and surfaces, add microdetail...
Reference
Name | Type | What it is |
|---|---|---|
Trigger | enhance this image | |
Prompt | author's sentence | Enhance this image to high resolution with rich fine details. Sharpen all textures and surfaces, add microdetail. |
Node | Krea2 Ostris Edit | Required custom node. |
LoRA weight | 0.8-1.0 | |
Aspect | portrait / square | Horizontal may misbehave. |
AD

No install required - run AI models on the cloud
BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).
Step by step
- Install the Ostris edit node pack.
- Load the source image and the LoRA.
- Prompt with the author's enhancement sentence.
- Generate and compare at 100 percent.
- Retry with a different seed if lighting shifted too much.
Examples
Portrait enhance
enhance this image. Enhance this image to high resolution with rich fine details. Sharpen all textures and surfaces, add microdetail to skin, hair and fabric.
Source: a soft 768px portrait
Product
enhance this image. Enhance this image to high resolution with rich fine details, sharpen the leather grain and stitching.
Source: a bag photo
Creative idea: old render refresh
enhance this image. Enhance this image to high resolution with rich fine details, keep composition and colors.
Source: a 2023 SD 1.5 render
Tips
- Best on portraits and objects with real texture.
- Follow with a conventional upscaler for size.
- Treat it as an experiment, as the author does.
Troubleshooting
Image content changed
Why it happens
Krea 2 is not an edit model.
How to fix it
Try another seed; use a dedicated edit model for precision.
Horizontal images distort
Why it happens
Known issue.
How to fix it
Use portrait or square sources.
AD

No install required - run AI models on the cloud
PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.
Questions
Trigger?
enhance this image.
Needs special nodes?
Yes, the Ostris Krea 2 edit node.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
Caucasian / Asian ethnicity slider for Krea 2: use the lowest value that works
Loraholic's ethnicity slider shifts facial features between Caucasian and East Asian appearance in Krea 2. Learn the -5 to 4 range, why low values are recommended and how to use it responsibly for character design.
By Captain
2026-10-02
Models
Anime Flat Style for Krea 2: bold cel-shaded 2D
Agino's Anime Flat Style LoRA gives Krea 2 clean anime artwork with bold flat colors and minimal shading. Learn weight, prompt structure and ideas for character designs and screencap-style scenes.
By Captain
2026-10-02
Models
Anything2RealCharacters V3 for Krea 2: turn 2D art into photorealistic people
AIGC_Singularity's Anything2RealCharacters V3 is an image-to-image stylization LoRA that converts anime and artistic inputs into photoreal characters while keeping identity. Learn the workflow, denoise and ideas.
By Captain
2026-10-03
Models
Krea2-Anime v1.5: an anime fine-tune that rewards detailed prompts
youneedanewname's Krea2-Anime turns Krea 2 into an anime model, but only shines with rich scene descriptions. Learn its prompting philosophy, tag plus prose structure, settings and ideas.
By Captain
2026-10-02
More guides
Models
FLUX.1 Dev: how to prompt it, best settings and creative ideas
A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.
By Captain
2026-09-30
Models
Stable Diffusion XL 1.0: prompts, settings and what it still does best
How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.
By Captain
2026-10-01
Models
Stable Diffusion 1.5: the classic model, prompted properly
Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.
By Captain
2026-10-02
Models
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
By Captain
2026-10-03
Models
Qwen-Image: long prompts, perfect text and bilingual posters
Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.
By Captain
2026-09-29
Models
SDXL-Lightning: four-step generation on any SDXL checkpoint
ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.
By Captain
2026-09-30

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026

