README.md

metadata

title: P-Q-Image-2.1
emoji: ⚡
colorFrom: indigo
colorTo: indigo
sdk: gradio
sdk_version: 6.28.0
python_version: '3.12'
app_file: app.py
pinned: false
hf_oauth: true
hf_oauth_scopes:
  - inference-api
  - write-repos
short_description: Few-step LoRA for Qwen-Image-2.1 (6-steps v0.2)
models:
  - PrunaAI/P-Q-Image-2.1
  - Qwen/Qwen-Image-2.1
license: other
license_name: qwen-research

P-Q-Image-2.1

Few-step LoRA adapters for Qwen/Qwen-Image-2.1. Same pipeline for text-to-image and image editing, no CFG.

Pick a Variant:

Variant	Steps	Notes
6-steps	6	v0.2 default. Faithful few-step distillation; best for editing.
6-steps-upsampled	6	v0.2. Distills prompt upsampling into the LoRA.
8-steps	8	v0.1, higher quality of that release.
5-steps	5	v0.1, faster, lower quality.

Model card: PrunaAI/P-Q-Image-2.1