OpenAI Launches ChatGPT Images 2.0, Producing 8 Coherent Images Per Session
OpenAI has just released an AI image generator built on its new GPT Image2 model — ChatGPT Images 2.0. The standout feature of this version is giving the AI a stronger "reasoning capability," allowing it to behave more like a logical creator when tackling complex visual tasks.

With Reasoning Planning, Image Generation Stops Being a "Guessing Game"
Unlike the earlier approach that generated images directly, Images 2.0 adds a deep logical planning system. When reasoning is activated, the AI first searches online information and analyzes user-uploaded files. By pre-reasoning the image structure and planning the layout, the resulting output aligns better with logical intuition instead of just piecing together materials. This advanced feature is currently accessible to ChatGPT Plus, Pro, Business, and Enterprise subscribers.

Coherence Breakthrough: Generate Up to 8 Images at Once for Comics and Design
In multi-image generation, the latest version marks a milestone. Images 2.0 can now produce up to 8 coherent images from a single prompt. Most impressively, the system strictly maintains consistency in character looks, object details, and overall visual style across different scene transitions. This capability dramatically lowers the barrier for creating long comic strips, social media series illustrations, or full interior design schemes.
Quality Upgrades and Multilingual Fine-Tuning
On the technical side, the new version boosts maximum resolution to 2K and offers aspect ratios from 3:1 to 1:3, making it ideal for film stills, pixel art, and other specific styles. To serve global audiences, the team has also fine-tuned text generation accuracy in Chinese, Japanese, Korean, Hindi, and Bengali, addressing common problems like text encoding errors and misinterpretations seen in earlier AI-generated images.
This update signals a shift in AI drawing from mere "pixel generation" to "understanding and creation," offering both professional designers and everyday users more efficient visual tools.
Related article
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
AI race won’t wait, nor will this TechCrunch Disrupt 25% discount
Every founder building in AI right now is asking the same question: Are we moving fast enough, and effectively enough? TechCrunch Disrupt 2026 puts you in the same room as the people wrestling with that existential question at the highest levels. Fro
Related Special Topic Recommendations
Comments (0)
0/500
OpenAI has just released an AI image generator built on its new GPT Image2 model — ChatGPT Images 2.0. The standout feature of this version is giving the AI a stronger "reasoning capability," allowing it to behave more like a logical creator when tackling complex visual tasks.

With Reasoning Planning, Image Generation Stops Being a "Guessing Game"
Unlike the earlier approach that generated images directly, Images 2.0 adds a deep logical planning system. When reasoning is activated, the AI first searches online information and analyzes user-uploaded files. By pre-reasoning the image structure and planning the layout, the resulting output aligns better with logical intuition instead of just piecing together materials. This advanced feature is currently accessible to ChatGPT Plus, Pro, Business, and Enterprise subscribers.

Coherence Breakthrough: Generate Up to 8 Images at Once for Comics and Design
In multi-image generation, the latest version marks a milestone. Images 2.0 can now produce up to 8 coherent images from a single prompt. Most impressively, the system strictly maintains consistency in character looks, object details, and overall visual style across different scene transitions. This capability dramatically lowers the barrier for creating long comic strips, social media series illustrations, or full interior design schemes.
Quality Upgrades and Multilingual Fine-Tuning
On the technical side, the new version boosts maximum resolution to 2K and offers aspect ratios from 3:1 to 1:3, making it ideal for film stills, pixel art, and other specific styles. To serve global audiences, the team has also fine-tuned text generation accuracy in Chinese, Japanese, Korean, Hindi, and Bengali, addressing common problems like text encoding errors and misinterpretations seen in earlier AI-generated images.
This update signals a shift in AI drawing from mere "pixel generation" to "understanding and creation," offering both professional designers and everyday users more efficient visual tools.
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
AI race won’t wait, nor will this TechCrunch Disrupt 25% discount
Every founder building in AI right now is asking the same question: Are we moving fast enough, and effectively enough? TechCrunch Disrupt 2026 puts you in the same room as the people wrestling with that existential question at the highest levels. Fro





Home






