Skip to content

EthenEthenEthen

Open Source Model Profile · FireRedTeam

FireRed-Image-Edit-1.0

FireRed-Image-Edit-1.0 is a 20.43B-parameter image-editing model from FireRedTeam. According to the model card, it targets high-fidelity, consistent edits across many scenarios.

Publisher
FireRedTeam
Task
image-to-image
Model type
Unknown
License
apache-2.0
Library
diffusers
Publication status
Accepted · not indexed

Model overview

FireRed-Image-Edit-1.0 is published by FireRedTeam as an image-to-image model. Safetensors metadata reports 20,430,401,088 parameters, about 20.43B. According to the model card, it is a general-purpose image-editing model for high-fidelity, consistent editing.

Recorded capabilities

General-purpose editing

According to the model card, FireRed-Image-Edit delivers high-fidelity editing with accurate instruction following and visual coherence.

Native editing and text preservation

According to the model card, the model is built directly from a text-to-image foundation model and maintains text styles with high fidelity.

Documented model zoo and example

According to the model card, the zoo lists the 1.0 editing model with distilled and text-to-image variants to be released, plus an inference.py editing example.

Publisher-reported REDEdit-Bench

According to the model card, REDEdit-Bench was built from over 3,000 collected images into 1,673 bilingual pairs, with inference and evaluation scripts and a comparison table.

Use cases in the source record

  • Instruction-guided image editing where instruction following, image quality, and text-style preservation matter, as described in the card.
  • Editing evaluation work referencing the card's REDEdit-Bench pairs and redbench inference and evaluation scripts.

Limitations and unknowns

  • No independently measured evaluation results were extracted; comparison scores are publisher-reported card claims.
  • No training data, compute, or hyperparameter detail was extracted from this record.
  • According to the model card, the REDEdit-Bench dataset itself will be available soon.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: FireRedTeam/FireRed-Image-Edit-1.0

Captured: Unknown. Processed: 2026-09-07T19:34:30.642374+00:00.

🤗 HuggingFace | 🖥️ Demo | 📄 Technical Report 🔥 FireRed-Image-Edit FireRed-Image-Edit is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios. ✨ Key Features Strong Editing Performance : FireRed-Image-Edit delivers leading open-source results with accurate instruction following, high image quality, and consistent visual coherence. Native Editing Capability : Built directly from text-to-image foundation model and endowed with editing capabilities. Text Style Preservation : Maintains text styles with high fidelity, achieving performance comparable to closed-source…

F001F002F003F004F005F006F008F009F010F011F012F013F014F015F016F017