Pith. sign in

REVIEW 6 cited by

Emu Edit: Precise Image Editing via Recognition and Generation Tasks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.10089 v1 pith:6Y5GUJZI submitted 2023-11-16 cs.CV cs.AIcs.LG

Emu Edit: Precise Image Editing via Recognition and Generation Tasks

classification cs.CV cs.AIcs.LG
keywords editingeditimagetasksmulti-taskgenerationinstruction-basedmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. However, current models in this domain often struggle with accurately executing user instructions. We present Emu Edit, a multi-task image editing model which sets state-of-the-art results in instruction-based image editing. To develop Emu Edit we train it to multi-task across an unprecedented range of tasks, such as region-based editing, free-form editing, and Computer Vision tasks, all of which are formulated as generative tasks. Additionally, to enhance Emu Edit's multi-task learning abilities, we provide it with learned task embeddings which guide the generation process towards the correct edit type. Both these elements are essential for Emu Edit's outstanding performance. Furthermore, we show that Emu Edit can generalize to new tasks, such as image inpainting, super-resolution, and compositions of editing tasks, with just a few labeled examples. This capability offers a significant advantage in scenarios where high-quality samples are scarce. Lastly, to facilitate a more rigorous and informed assessment of instructable image editing models, we release a new challenging and versatile benchmark that includes seven different image editing tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

    cs.CV 2025-04 unverdicted novelty 7.0

    ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.

  2. CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

    cs.CV 2026-07 conditional novelty 6.0

    SFT+GRPO training on CanvasCraft teaches an MLLM to orchestrate heterogeneous visual tools for long-horizon image creation and editing.

  3. SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

    cs.CV 2026-04 unverdicted novelty 6.0

    SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.

  4. HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes

    cs.CV 2026-04 unverdicted novelty 6.0

    HorizonWeaver enables photorealistic, instruction-driven multi-level editing of complex driving scenes with improved generalization via a new paired dataset, language-guided masks, and joint training losses.

  5. FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space

    cs.GR 2025-06 unverdicted novelty 6.0

    FLUX.1 Kontext unifies image generation and editing via flow matching and sequence concatenation, delivering improved multi-turn consistency and speed on the new KontextBench benchmark.

  6. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

    cs.CV 2024-03 conditional novelty 6.0

    Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.