img-forge v2

Prompt Guide & Gallery

How the pipeline transforms your words into images. Compare quality tiers and models, browse every image we’ve generated, and learn prompting techniques.

Explore Gallery Generate an image →

Same prompt, different tiers

Each tier uses a different model. Draft runs SDXL Lightning for speed, Standard uses FLUX Klein 4B, Premium uses FLUX.2 Dev, Ultra uses Gemini 2.5 Flash, and Ultra+ uses Gemini 3.1 Flash for maximum fidelity. Higher tiers inject quality boosters and style defaults.

Red fox - draft
Draft
SDXL Lightning
“a red fox in a snowy forest”
No enhancement
a red fox in a snowy forest
Red fox - standard
Standard
FLUX Klein 4B
“a red fox in a snowy forest”
Enhanced to
a red fox in a snowy forest, high quality, detailed
Red fox - premium
Premium
FLUX.2 Dev
“a red fox in a snowy forest”
Enhanced to
a red fox in a snowy forest, masterpiece, best quality, highly detailed, sharp focus, 8k, photorealistic
Red fox - ultra
Ultra
Gemini 2.5 Flash
“a red fox in a snowy forest”
Enhanced to
a red fox in a snowy forest, highly detailed, professional quality, vivid colors, photorealistic
Red fox - ultra+
Ultra+
Gemini 3.1 Flash
“a red fox in a snowy forest”
Enhanced to
a red fox in a snowy forest, masterpiece, best quality, ultra detailed, 8k resolution, photorealistic

Generate UI concepts in seconds

Skip the blank canvas. Use img-forge to rapidly generate UI concept art — from lo-fi sketches on draft tier to polished visual mockups on ultra. Part of the Stackbilt ecosystem for shipping faster.

How enhancement works

Every prompt passes through a three-stage pure-function pipeline. No AI calls until generation — the enhancement is deterministic and transparent.

Example: “a robot” at premium tier
Input
a robot
Analyze
subject: a robot · style: none · complexity: simple · gaps: style, lighting, composition
Expand
a robot, masterpiece, best quality, highly detailed, sharp focus, 8k, photorealistic
Model
Premium tier → FLUX.2 Dev (25 steps, 1024×768)
Negative
Skipped — FLUX models do not support negative prompts. For Draft (SDXL Lightning), negative prompts are applied: lowres, bad anatomy, bad hands, text, error, blurry…

Write better prompts

The pipeline helps, but a well-written prompt still makes the biggest difference. A few guidelines for getting the most out of each generation.

01

Be specific about your subject

“a robot” works, but “a weathered industrial robot standing in an abandoned factory” gives the model dramatically more to work with. Nouns and adjectives are your primary tools.

02

Name your style

The analyzer detects style keywords like watercolor, photorealistic, anime, oil painting, or 3d render. Including one steers the entire output and prevents the pipeline from injecting a default.

03

Mention lighting & composition

Terms like golden hour, dramatic shadows, close-up, or wide angle are detected by the analyzer. When present, the pipeline skips injecting defaults and trusts your intent.

04

Choose the right tier

Draft (SDXL Lightning) — fastest, free. Standard (FLUX Klein) — fast 4-step FLUX. Premium (FLUX.2 Dev) — 25-step generation. Ultra (Gemini 2.5 Flash) — Google’s multimodal model. Ultra+ (Gemini 3.1 Flash) — latest Gemini image generation.