⚗ Alchemica Sampler (advanced, presets + options)

Modular sampler for Krea 2 Turbo: presets + chainable options, two stages low -> high resolution.

By Nessuno76·Created 18 days ago·Updated about 22 hours ago· 2

◄seed0►

◄presetalchemica_turbo►

◄profile▾►

◄denoise1.00►

◄preview_methodlatent2rgb (fast)►

◄degrid0.0►

Category⚗ AlchemicaMente/sampling

Inputs (13)

Name	Type	Default	Description
model	MODEL		—
positive	CONDITIONING		—
latent_image	LATENT		Latent at the FINAL resolution. In two-stage mode the first stage works at a fraction of it.
seed	INT	00–18446744073709550000	—
preset	COMBO	alchemica_turbo	10 options: reference_euler_simple, alchemica_dual, alchemica_turbo, alchemica_quality, alchemica_hires_2stage, photo_calibrated, +4
profile	COMBO		(auto) = recognises the checkpoint and uses its calibration profile. Needed by the foto_tarata presets and by -1 values
denoise	FLOAT	1.000–1	1.0 = from scratch. <1 = img2img (disables two-stage mode).
negativeopt	CONDITIONING		Used only with negative_mode = text and cfg > 1
refiner_modelopt	MODEL		Optional: second stage with a different model
optsopt	ALCHEMICA_OPTS		Overrides the preset entries
vaeopt	VAE		Optional: the final image is decoded and SHOWN in this node, and returned on the 'image' output (like the Efficiency KSampler)
preview_methodopt	COMBO	latent2rgb (fast)	Live preview while sampling. latent2rgb = instant, a bit soft; taesd = sharper (needs the TAE model in models/vae_approx, otherwise latent2rgb); 'ComfyUI setting' = whatever ComfyUI is set to (often none)
degridopt	FLOAT	0.00–10	Only with a VAE connected: removes the faint 2-pixel line grid of Krea 2's VAE from the image shown and returned here (the latent is untouched). Max correction in grey levels: 2 = recommended, 0 = off