CivArchive
    [TheRealReal] Krea 2 · Two-Pass Refine Workflow (no upscaler) - v1.0
    NSFW
    Preview 144592920
    Preview 144592961

    Krea 2 · Two-Pass Refine Workflow (no upscaler)

    A clean two-pass text-to-image workflow for Krea 2 — the exact pipeline I use for my gravure / portrait LoRAs. Pass 1 lays down the composition, pass 2 re-samples at 1.9× for texture and skin detail, then a light color match pulls the result back to pass-1 tones. No tiled upscaler: the output is 1216×1824 straight from pass 2.

    PIPELINE

    - UNET (Krea 2) → LoRA 1 (character) → LoRA 2 (style base, bypassed by default)

    - Pass 1 — KSamplerAdvanced, er_sde / simple, 7 steps, CFG 1, 640×960, shift 0 (no ModelSampling node)

    - Pass-1 decode is kept as a preview and as the ColorMatch reference

    - LatentUpscaleBy, bislerp ×1.9

    - Pass 2 — KSamplerAdvanced, euler / simple, 9 steps starting at step 4, CFG 1, negative zeroed with ConditioningZeroOut

    - Decode → ColorMatch (hm-mkl-hm, strength 0.22) → SaveImage

    MODELS

    - UNET: any Krea 2 checkpoint (Turbo or a mix) — set the file for your machine

    - Text encoder: qwen3vl_4b_fp8_scaled.safetensors, CLIPLoader type = krea2

    - VAE: qwen_image_vae.safetensors

    - LoRA slot 1 = your character LoRA; slot 2 = a style LoRA (un-bypass it to use it)

    REQUIREMENTS

    - ComfyUI with Krea 2 support (CLIPLoader must list "krea2")

    - ComfyUI-KJNodes for ColorMatch — on newer KJNodes swap in ColorMatchV2 (image_target / image_ref inputs are in the opposite order). Everything else is core.

    HOW TO PROMPT

    Write full sentences in caption order: framing → camera height / distance → pose (hands, legs) → expression → hair → outfit and fabric → light direction and quality → environment. At CFG 1 the negative prompt does nothing, so describe what you want instead of what you don't. A README note on the canvas repeats all of this.

    Tips: keep the portrait aspect (640×960 → 1216×1824); for landscape use 960×640. If pass 2 drifts too far from pass 1, raise start_at_step to 5–6; for more change, lower it to 3.

    Description

    Krea 2 · Two-Pass Refine Workflow (no upscaler)

    A clean two-pass text-to-image workflow for Krea 2 — the exact pipeline I use for my gravure / portrait LoRAs. Pass 1 lays down the composition, pass 2 re-samples at 1.9× for texture and skin detail, then a light color match pulls the result back to pass-1 tones. No tiled upscaler: the output is 1216×1824 straight from pass 2.

    PIPELINE

    - UNET (Krea 2) → LoRA 1 (character) → LoRA 2 (style base, bypassed by default)

    - Pass 1 — KSamplerAdvanced, er_sde / simple, 7 steps, CFG 1, 640×960, shift 0 (no ModelSampling node)

    - Pass-1 decode is kept as a preview and as the ColorMatch reference

    - LatentUpscaleBy, bislerp ×1.9 up to 3 before you see random renders

    - Pass 2 — KSamplerAdvanced, euler / simple, 9 steps starting at step 4, CFG 1, negative zeroed with ConditioningZeroOut

    - Decode → ColorMatch (hm-mkl-hm, strength 0.22) → SaveImage

    MODELS

    - UNET: any Krea 2 checkpoint (Turbo or a mix) — set the file for your machine

    - Text encoder: qwen3vl_4b_fp8_scaled.safetensors, CLIPLoader type = krea2

    - VAE: qwen_image_vae.safetensors

    - LoRA slot 1 = your character LoRA; slot 2 = a style LoRA (un-bypass it to use it)

    REQUIREMENTS

    - ComfyUI with Krea 2 support (CLIPLoader must list "krea2")

    - ComfyUI-KJNodes for ColorMatch — on newer KJNodes swap in ColorMatchV2 (image_target / image_ref inputs are in the opposite order). Everything else is core.

    HOW TO PROMPT

    Write full sentences in caption order: framing → camera height / distance → pose (hands, legs) → expression → hair → outfit and fabric → light direction and quality → environment. At CFG 1 the negative prompt does nothing, so describe what you want instead of what you don't. A README note on the canvas repeats all of this.

    Tips: keep the portrait aspect (640×960 → 1216×1824); for landscape use 960×640. If pass 2 drifts too far from pass 1, raise start_at_step to 5–6; for more change, lower it to 3.

    FAQ

    Comments (6)

    2TheMaxOct 16, 2026
    CivitAI

    Hi, I realize that the final pass will affect the final image face. I also try several model to test, any solution or guide you can provide, anyway, your work work is great!

    bestyiever292
    Author
    Oct 16, 2026

    did you use same model for both path? try use only turbo models otherwise need to adjust steps

    2TheMaxOct 16, 2026

    @bestyiever292 Thx for reply. I'm using int8 model. My first pass is 8, is that at the Pass 2 i lower the steps or follow? i am using your default setting😄

    2TheMaxOct 16, 2026

    @bestyiever292 Sorry for my noob question, i'm quite new in comfyui😆my gpu 3060, so i only can play int8 model😆

    bestyiever292
    Author
    Oct 16, 2026

    @2TheMax Pass 2 steps: 9cfg: 1start: 4 end: 10

    2TheMaxOct 16, 2026

    @bestyiever292 Thank you for your fast response!🙏🙇🏽it work like a champion!!! & i had learn new thing🙇🏽Thank you again.

    Workflows
    Krea 2

    Details

    Downloads
    1,137
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/3/2026
    Updated
    11/22/2026
    Deleted
    -

    Files

    krea2_moody_workflow.json

    Mirrors

    CivitAI (1 mirrors)