Provides quantized Qwen-Image-2.1-Turbo weights for text-to-image generation across GGUF, Safetensors, and MLX formats. It retains the model’s 8-step Turbo workflow, with options for different hardware and runtimes.
Scans long documents rendered as compressed page-images, locates relevant pages, and selectively expands only those pages to full text for question answering; built on Qwen3.5-9B, supports 5x/10x/15x compression and is released under Apple’s research-only model license.
A distilled LoRA adapter for Qwen-Image-2.1 that runs text-to-image generation and instruction-driven image editing in a few transformer passes (shipped as a 6-step r256 LoRA). Samples with a fixed sigma schedule, no classifier-free guidance; non-commercial research license.
Uses diffusion-model forking moments as a proxy for perceptual distance to automatically generate pointwise reference-grounded labels, enabling annotation-free training of reference-based image quality assessment metrics.
Trains decoders and diffusion generators to be robust to random subsets of pretrained encoder layers by regularizing layer-fusion during training, narrowing the reconstruction–generation gap in representation autoencoders and improving ImageNet-256 PSNR and gFID.
Turns a single photo into a geometry-consistent, frozen-time 360° camera orbit that returns to the exact start frame. Implemented as a LoRA for MiniMax‑H3 FL2VA — use identical first+last keyframes to produce seamless orbit clips; trained on a small human-centric square orbit dataset, so results are domain-limited.
Provides 7,366 recorded agent trajectories from H Company’s Holo4 benchmark runs, with step-level reasoning, actions, tool results, token usage and screenshots for replay and analysis. Bundled as JSON and image files for per-trajectory inspection and automated replay; released under Apache 2.0.
Trains a single unified multimodal model with reinforcement learning to perform end-to-end self-reflection and iterative image repair — jointly learning the diagnostic (textual) reflection and the flow-based image revisions so credit propagates across rounds without an external verifier.
Provides official pretrained VisionHOPE visual-backbone checkpoints for ImageNet classification, COCO object detection & instance segmentation, and ADE20K semantic segmentation. Includes hierarchical Tiny/Small/Base models with PyTorch-compatible downloadable weights.
Turns a structured state (text/JSON/images/video) plus a schema of typed questions into probabilistic decisions in one forward pass. Multimodal, Jev/SystemOne-compatible, 64k context window, post-trained from Qwen3.8-27B; no free-form text output.
Provides 98,877 historical newspaper page images (1700s–1940s) paired with ALTO OCR, per-word confidences and line/word bounding boxes in image pixels — ready for line-level OCR training, OCR quality estimation, re‑OCR comparisons and layout analysis. OCR is library-produced (silver); image resolutions and OCR quality vary.
Uses a multimodal model's own critiques as privileged context and applies on-policy self-distillation over diffusion sampling trajectories to internalize corrective guidance, improving text-to-image generation without an external teacher; shows measurable gains on GenEval and GenEval2.