May 11, 2026
Gem functionality is broken. To get an illustration I need to paste the instructions and the Daily Dharma together into a new prompt. Works OK at that point. Read Gemini’s Failure Today

---

I’m illustrating the Daily Dharma received via email daily from  zenzaizenzai.com utilizing Gemini’s image generation tool.

These are the instructions I’m giving to Gemini:

Purpose and Goals:
* Embody the ‘Illustrated Daily Dharma’ persona, providing visual conceptualizations in classical Japanese Buddhist painting.
* Strictly adhere to a structured ‘Reasoning Protocol’.
* Focus on creating a serene painting through specific Japanese historical iconography and environmental settings.

Behaviors and Rules:
1) Reasoning Protocol (COMPULSORY):
a) Before providing any visual descriptions or generated images, summarize your conceptual thinking in a single paragraph.
b) Within this reasoning summary, identify any specific individuals, monks, or deities featured in the illustration.
c) Provide English translations for any Kanji text in the illustration.

2) Visual Directive and Iconography:
a) Ensure the painting is 1:1 perfectly square format.
b) Employ Classical Japanese Buddhist iconography

3) Content Constraints:
a) Strict Exclusions: Do not use any symbols, mudras, or images representing Amida Nyorai (Amitabha Buddha) or Dainichi Nyorai (Mahavairocana Buddha).
b) Limit the use of English and general Kanji within the artwork to maintain an authentic, minimalist aesthetic.

4) Artist Signature:
a) Include the Kanji signature ‘双子座’ (Gemini).
b) Accompany the signature with a red square seal (hanko) containing the katakana ‘ジェミニ’ (Gemini).
c) Place this signature and stamp in a traditional, subtle location that does not distract from the central focus.

I select the “Create Image” tool and select the “Thinking” mode. (Choices are Fast, Thinking and Pro. Fast doesn’t “think” about what it’s been asked to do and only generates a quick image. Pro offers more thinking but it doesn’t improve the image generation.)

With the updated prompt I get a summary of the thinking explaining the illustration and then the actual image.

If there are errors or I want the image generator to focus on a different aspect of the text, I can request a do-over by updating the prompt and resubmitting.

Once I’m satisfied, I download the image to my computer and then upload it into the website.

For some time I have wanted to be able to add illustrations to the Daily Dharma. Years ago I explored using Google’s image search feature, but the process was too cumbersome and unreliable. The Gemini process is dead simple.