I asked GPT 5 for a minimalist workflow to process a dual narrowband OSC image in PixInsight. I asked it to consider all the freely available 3rd party plug ins as well native PI processes and to recommend the best process for each step. I constrained it to avoid separating/recombining stars as well use of masks, just a very simple direct process to a final image. I understand how much power PI has under the hood and this is just my way of diving in.
Below is what it gave me, what do you think?
———————————————————-
DynamicCrop
Remove stacking artifacts and edge gradients.
Gradient Removal
GraXpert (Astro model, Medium strength)
or ABE (Degree 2–3, Subtraction) if you want native only.
Linear Noise Reduction
MURE Denoise (if gain/RN known)
or MLT (5 layers, conservative thresholds) if not.
Channel Extraction & OIII Mix
Extract R = Ha, G/B = OIII.
PixelMath:
OIII = 0.7*G + 0.3*B
(adjust weights by SNR).
LinearFit
Reference = Ha, apply to OIII.
HOO Combine (Normalized)
PixelMath:
Hn = Ha/(Ha+OIII+1e-6);
On = OIII/(Ha+OIII+1e-6);
R: Hn
G: 0.2*Hn + 0.8*On
B: On
BackgroundNeutralization
Small preview on true background.
Stretch
GHS (2 passes) → HT for fine black/midpoint placement.
Local Contrast
LHE (Kernel ~64, Amount 0.3) global.
Color Tuning
Curves (global saturation/hue).
SCNR (Green, 0.25) only if needed.
CorrectMagentaStars (global).