AIKSK/Kromoss 8-Step Text-to-Image

A compact Kromoss text-to-image recipe pairing the Kromoss INT8 model with the connected DMD2 acceleration LoRA. Its active sampler is set to eight diffusion steps. Main features: - kromoss_int8_convrot.safetensors with 8-steps-dmd2-lora.safetensors at strength 1. - Qwen3.5 9B BF16 text encoder and FLUX.2 VAE; 1024 x 1024 latent canvas. - Euler sampler at 8 steps, CFG 1, simple scheduler, fixed seed 9527; one SaveImage output. Suggested workflow: 1. Install the Kromoss model, DMD2 LoRA, text encoder, and VAE, then load the JSON. 2. Edit the text prompt and generate a baseline at the supplied e

<iframe src="https://silytics.si/embed/item/a6785137-6282-4e8f-b197-163dac222d80" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 26 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.