Uncensored Qwen-Image-2.1 GGUF drops refusal rate from 100% to 5% at 4.68GB on a laptop
alexcovo_eth · x · 2026-09-24
A community release (pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF) offers an uncensored variant of Qwen-Image-2.1 that only requires swapping the text encoder:
- Q4KM quantization is just 4.68GB and runs locally on a laptop
- Refusal rate drops from 100% to 5% with no degradation on normal prompts
- Supports editing with 10 reference images and native transparency (stickers/cutouts, no masking step)
- Works with ComfyUI and city96 GGUF loaders
Related event: Uncensored Qwen-Image-2.1 Leaks, Refusal Rate Drops to 5%(2 posts)→
More from Multimodal
- Generating accurate 3D building models from 150 planning PDFs with new Gemini model — fofrAI · 2026-11-11
- Stanford's DyCraft Uses Agentic Decomposition to Cut Physical Errors in Long-Horizon 4D Scene Generation — StanfordUniversity · 2026-11-11
- Midjourney SREF pick: --2523103199 for loose pencil-sketch portraits — tisch_eins · 2026-11-11
- H3 Image Tips: 16MP via ComfyUI Workflow Plus Detailed Prompts Yields Best Results — gatortux · 2026-11-11
- Gemini-generated endless loop of quantum cryostats self-assembling — hapticdata · 2026-11-11
- Dad brings his daughter's crayon drawings to life with AI for $1.75, and it's unsettling — Illustrious_Ad_4292 · 2026-11-11