Viggle Turbo v0.2.1 (preview) — 6-step Qwen-Image-2.1

A DMD-distilled student of Qwen-Image-2.1 that generates and edits in 6 sampling steps, with no classifier-free guidance. Leave the reference images empty for text-to-image; add one to three of them to edit, compose or transfer style. The size menu switches to the editing buckets as soon as a reference is attached.

v0.2: much better sample diversity than v0.1 (intra-prompt diversity 0.97× the 40-step base model, up from 0.75×) and closer prompt adherence / composition to the base model. 2026-09-24: same weights, now sampled on 6 steps instead of 5 - the extra step splits the highest-noise segment again, which removes the last of the composition drift (0% of prompts vs 4% at 5 steps) and lifts diversity from 0.93× to 0.97×. v0.2.1 (2026-09-24): the step-700 checkpoint of the same run (v0.2 was step 600) - a little sharper, diversity 0.98×, still 0% drift. Still a preview: complicated edits (multi-reference composition, face swaps, identity-preserving edits) remain weaker than the 40-step base model.

Weights: v0.2.1 LoRA r256 from Viggle/Qwen-Image-2.1-viggle-turbo.
Output size
3 8

Rewrite the prompt with the official Qwen-Image prompt-enhancement instructions (runs on the built-in Qwen3-VL text encoder, +4–15 s). The text actually sent is shown under the result.
Examples · results pre-rendered by this model — click a row to load it (6 steps, prompt enhancement on, unless the status line says otherwise)
Prompt Reference 1 (optional) Reference 2 (optional) Reference 3 (optional) Result

Model: Viggle/Qwen-Image-2.1-viggle-turbo · Built with Qwen — distilled from Qwen/Qwen-Image-2.1, which is released under the Qwen RESEARCH LICENSE AGREEMENT (non-commercial: research or evaluation purposes only). This demo inherits that restriction.