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.
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. Th...
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.
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.
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.
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.
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.
Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs.
The paper introduces Endpoint‑Calibrated Transport (ECT), a closed‑form, training‑free image editor that performs inversion‑free editing with a single temporal field evaluation. ECT leverages a duality in variance‑preserving one‑step models to compute a local angular semantic tangent and a clean endpoint displacement from one source‑target query at a shared noisy state. By integrating the tangent over the remaining VP angle and correcting the extrapolation with the endpoint displacement, ECT requires only one noise level, two text conditions in one denoiser batch, and a single latent update, achieving stable quality gains in very short editing time.
Edit‑VAR is a training‑free, inversion‑free framework that uses a pretrained visual autoregressive video model for text‑guided video editing. It encodes the source video into multi‑scale discrete tokens and applies probability‑guided conditional token replacement, attention‑guided token‑wise and scale‑aware modulation, and scale‑decoupled generation to preserve source appearance while enabling precise edits. The method also includes residual‑guided token pruning to reduce inference cost, and experimental results show it outperforms existing training‑free video editing methods in fidelity, source preservation, temporal coherence, and efficiency.
arXiv:2609.36843v1 Announce Type: new Abstract: Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World m...
PreciseEdit is a new one‑step image editing framework that improves semantic transport by applying strong target‑directed changes only along reliable directions and spatial locations. It is model‑agnostic, training‑free, and inversion‑free, and uses a dual‑noise‑scale strategy to balance strong editing with background fidelity and structural consistency. Experiments on PIE‑Bench show that PreciseEdit outperforms existing methods across a range of editing tasks.
The paper introduces WeGenEditBench, a benchmark with 2,740 evaluation instances and 148 task types for image editing, focusing on local failure detection and prioritization for model improvement. It also presents WeGenEvoStudio, a multi‑agent harness that supports recursive self‑improvement by diagnosing failures, constructing retrieval‑grounded data, and adapting models. Experiments show that models such as GPT‑Image‑2 and Seedream‑5.0‑Pro excel in single‑image and text‑intensive editing, and evolution experiments demonstrate significant targeted gains on selected benchmarks.