Built with Qwen. A few-step distilled student of Qwen/Qwen-Image-2.1, trained by Viggle with Distribution Matching Distillation. It does both text-to-image and instruction-driven editing with 1–3 reference images in 6 transformer passes instead of 40, with no classifier-free guidance. src="https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/assets/viggleturbopromo.mp4"> About 5× faster than the 40-step base model end to end, and very competitive with it in quality: on the official Qwen examples the two are hard to tell apart on most prompts, and on some — dense layouts like the character style infographic — we prefer the turbo's render. See for yourself in the Comparison…
Open weights
other
7.1B parameters
diffusers
We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility. Four key improvements define this release: - Compact and Efficient — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost. - Native Transparency, Unified Creation and Editing — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one…
Open weights
other
7.1B parameters
diffusers
Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model family with 6B parameters. Currently there are four variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image – The foundation model behind Z-Image-Turbo. Z-Image focuses on high-quality generation, rich…
Open weights
apache-2.0
6.2B parameters
diffusers
Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details. - For individuals and organizations with annual revenue above $1M: please contact us to get an Enterprise License. For local or self-hosted use, we recommend ComfyUI for node-based UI inference, or diffusers or GitHub for programmatic use. - Text Encoders： This model was trained on a wide variety of data, including synthetic data and…
Access requested at publisher
other
8.1B parameters
diffusers
The text-to-image prompt rewriter for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL 9B that turns a short request into a detailed English prompt plus a recommended aspect ratio, with its refusal behaviour reduced by Heretic directional ablation. bf16, same shapes and parameter count as the source. systemprompt.txt is included and required (the unmodified file from the source repo). for image edits. Measured by Heretic on mlabonne/harmfulbehaviors (refusals) and mlabonne/harmlessalpaca (KL divergence, the damage to ordinary behaviour), with Heretic's default system prompt. The first row is an independent evaluation of the exported weights (evaluatemodel); the search's own figure for the same trial…
Open weights
other
9.4B parameters
262,144 tokens
NVFP4 (4-bit floating point, W4A4) build of darrellbest/Qwen-Image-2.1-PE-T2I-Heretic, the refusal-ablated text-to-image prompt rewriter for Qwen-Image-2.1. For vLLM on NVIDIA Blackwell GPUs, which run NVFP4 natively. 11 GB instead of 18 GB. systemprompt.txt is included and required, exactly as for the original. The linear-attention layers carry a recurrent state and the vision tower encodes the input image; both were left in bf16, as other quantizations of this model family do. That is why the file is 11 GB rather than ~6 GB. Made with llm-compressor 0.13.0 (QuantizationModifier, scheme="NVFP4"), calibrated on 64 samples in the model's real input format: its own system prompt and a short…
Open weights
other
9.4B parameters
262,144 tokens
