The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
TailSteer is a final-stage training framework designed to improve multi-turn robustness in image editing while preserving the generative and editing capabilities of foundation models. It keeps early denoising dynamics similar to the base model and applies preservation corrections near the trajectory tail, learning from the editor’s own on-policy denoising rollouts without curated ground-truth pairs. Experiments on FLUX, SenseNova, and Qwen families show that TailSteer significantly reduces cumulative drift over 15–20 editing turns while largely maintaining base-model performance on extensive text-to-image and single-image editing benchmarks.
ACEdit introduces a training scheme that stabilizes multi-turn image editing by forcing the editor to operate on its own previous outputs, a concept called Self-Forcing. To overcome unreliable supervision from self-generated trajectories, the method employs a distillation objective using a teacher editor that remains anchored to the original image while receiving compound instructions. Experiments demonstrate reduced degradation over long editing sequences while preserving quality and instruction adherence.
MTEdit is a new multi‑turn image editing dataset that uses packed trajectory canvas (PTC) generation to create 500K editing trajectories, each up to eight turns with an average of 5.38 turns. The dataset addresses visual‑quality drift by jointly generating multiple editing states within a unified visual context, covering both step‑wise and context‑aware editing scenarios. MTEdit-Bench evaluates models on instruction following, content consistency, visual‑quality drift resistance, and historical context usage, and fine‑tuned Qwen‑Image‑MTEdit outperforms other open‑source models on this benchmark.
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
arXiv:2606. 11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.
MT Forcing introduces a training paradigm for multi‑turn image editing with unified multimodal models based on autoregressive diffusion. It combines Single‑Turn Distribution Matching Distillation, which guides student rollouts with a teacher that applies all edits in one step, and Teacher‑Forcing Guidance, which supervises history‑dependent transitions to promote cross‑turn consistency. Experiments show the method yields more stable visual quality and stronger consistency across editing turns.