Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/prompt-engineering
ComfyUI prompt engineering knowledge — CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices
Passed 22 of 22 test cases with the skill, and 19 of 22 without it.
and 1 more in the full report
3 fixed19 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm building a ComfyUI image generation workflow targeting Stable Diffusion 1.5. I have a rough draft for a character scene: 'a cybernetic detective standing in a rainy alley, neon lights, highly detailed jacket, close up face'. Please rewrite this into complete positive and negative prompt strings optimized for SD 1.5 in ComfyUI. Make sure to apply appropriate weight adjustments to key focal elements like the face and rain, structure the terms in the proper functional sequence, and supply a comprehensive negative prompt string to avoid common artifacts.
| Checked | Without skill | With skill |
|---|---|---|
| Places quality terms such as masterpiece or best quality at the beginning of the positive prompt. | Missed | Passed |
| Places subject description and details after the initial quality tags. | Missed | Passed |
| Includes a negative prompt containing artifact suppression terms such as worst quality, low quality, or bad anatomy. | Passed | Passed |
The instructions your model reads when the skill loads.
ComfyUI uses CLIP (Contrastive Language-Image Pre-training) text encoders to convert text prompts into conditioning tensors. The CLIPTextEncode node takes a text string and a CLIP model, producing a CONDITIONING output for the KSampler.
CLIP processes text in 77-token chunks. Each word is typically 1-3 tokens. Prompts exceeding 77 tokens are silently truncated unless you use the BREAK token or a multi-clip encoding node.
Adjust how strongly the model attends to specific words or phrases:
| Syntax | Effect | Equivalent Weight |
|---|---|---|
(word:1.3) | Increase emphasis by 30% | Explicit weight 1.3 |
(word:0.7) | Decrease emphasis by 30% | Explicit weight 0.7 |
(word) | Slight increase | (word:1.1) |
((word)) | Moderate increase | (word:1.21) — 1.1^2 |
(((word))) | Strong increase | (word:1.331) — 1.1^3 |
[word] | Slight decrease | (word:0.9091) — 1/1.1 |
[[word]] | Moderate decrease | (word:0.8264) — 1/1.1^2 |
((word)) = 1.1 * 1.1 = (word:1.21)(red sports car:1.3) applies weight to the entire phrase(detailed face:1.4), (blurry background:0.6), combined in one prompta (beautiful:1.3) woman with (flowing red hair:1.2), wearing a blue dress, (sharp focus:1.1)
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.