by inclusionAI
Open-weights 6B unified text-to-image and instruction-based image editing model family from inclusionAI.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
LLaDA-Image is a 6B-parameter image generation and editing model family from inclusionAI. A single checkpoint handles text-to-image generation and reference-preserving, instruction-guided editing. According to the repository, both the backbone and the DiT are diffusion models trained in a unified framework, with image-only pre-training and mid-training before paired language supervision and joint generation–editing training.
The family has two variants: the Base model (50 sampling steps) and LLaDA-Image-Turbo (4 steps, distilled with Twin-DMD). Both are published in BF16 and FP8 versions. They support text-to-image generation, VQ-conditioned generation, reference-image editing, and Chinese–English text rendering, including poster generation. The authors report overall scores of 53.53 (English) and 53.38 (Chinese) on Qwen-Image-Bench.
The repository provides checkpoints and Diffusers-based inference code (tested with Python 3.11, PyTorch 2.8, Diffusers 0.39.0). Checkpoints are on Hugging Face and ModelScope, and community ComfyUI versions exist. Training code is listed as "coming soon". The license was not stated in the material provided.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source 6B text-to-image generator and editor producing realistic photos, posters and infographics. Comes in base (50 steps) and turbo (4 steps) versions in BF16 and FP8.
Closest neighbours by meaning, not just by category.
Model · inclusionAI
Open-weights 6B text-to-image model for UI, infographics and posters, with 2K output and RGBA transparency.
Model
Open-weights 6B text-to-image model family from Alibaba's Tongyi-MAI lab, with a fast 8-step Turbo variant.
Model · OpenAI
OpenAI's image generation and editing model family, accessed via the API and ChatGPT.
Model · Princeton
Fully open 3B text-to-image diffusion model from Princeton with released weights, training code, and data pipeline.
Model · OpenMOSS
Open-weights 5B text-to-image model family from OpenMOSS with native JSON bounding-box layout control and text rendering.
Model · OpenAI
OpenAI's image generation and editing model in ChatGPT and the API, with Sunburst and Flare variants.