Back to Models
StepFunAIOpen Source

NextStep-1.1

NextStep-1.1 is a vision large model (VLM) developed by StepFunAI. It is a foundation model with a parameter scale of approximately 150.0B and is released under the Apache 2.0 license.

Parameters

150.0B

Context Window

License

Apache 2.0

Release Date

2025-12-24

API Pricing

API pricing for this model is not yet available

Strengths

  • Large 150B parameter scale
  • Advanced visual understanding capability
  • Open Apache 2.0 license

Weaknesses

  • High computational cost due to scale
  • Resource consumption during inference
  • Hardware requirements for operation

Use Cases

  • Advanced image analysis
  • Understanding and processing visual information
  • Open-source visual AI development

Deep Analysis

Architecture

Autoregressive Image Generation

Continuous token generation

Training Steps

500K total

200K→500K from NextStep-1

Resolutions

256px + 512px

Multi-resolution training

Release Date

2025

ICLR 2026 Oral

Post-Training

NextStep-GRPO

Stabilized reinforcement learning

License

Open-source

Strengths

  • ICLR 2026 Oral presentation
  • SOTA autoregressive image generation with continuous tokens
  • Addresses instability issues of original NextStep-1
  • Significant improvement in image quality and text rendering
  • Open-source research project

Weaknesses

  • Research model, not production-ready
  • Limited to image generation
  • Requires significant compute for training

Competitor Comparison

ModelArenaSWEGPQAPrice
NextStep-1---Free (open)
DALL-E 3---Paid
Stable Diffusion 3---Free (open)

NextStep-1.1 is StepFun's improved autoregressive image generation model, presented as an ICLR 2026 Oral paper. It addresses visualization failures from NextStep-1 through extended training (500K steps) and a stabilized post-training strategy (NextStep-GRPO).

Analysis generated: 2026-05-24