Sign inGet started
Model · Civitai

AIKSK/FLUX 3 Klein Multi-Reference 1-10

FLUX 3 Image Klein multi-reference workflow. Feed one to ten reference images and tell the model which one owns the character, which one owns the outfit and which one owns the scene. Main features: - Built on the distilled FLUX 3 Image Klein checkpoint (flux3_image_klein_sd_int8_convrot + qwen3vl_4b text encoder + flux2 VAE) - ReferenceMultiLatent packs up to 10 reference images into a single conditioning tensor; reference them in the caption as ref_image_0 through ref_image_9 - 16 steps, CFG 1, euler/simple, denoise 1.0 - ConditioningZeroOut lets you disable a reference slot without deleting

Author / organizationAIKSK
Downloads20 (as reported by Civitai)
Likes2
Tasktext-to-image
Created18 October 2026
Last updated at source—
text-to-imageworkflowsotherflux 3 kleinai-kskrunninghubworkflowcomfyui10 imagesreference imagemulti referenceflux3
Embed this entry
<iframe src="https://silytics.si/embed/item/662f7ee0-1bfd-4995-bdd3-5ee3151154af" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from AIKSK

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.