Answer: Use a small set of reference images when one image defines the content and another defines the style, layout, or other visual direction; identify each image by order, explain how the images relate, and use spatial terms such as foreground, background, left, and right when combining elements. Status: Confirmed Entry: tool/chatgpt/features/multiple-reference-images Revision: 1 Digest: sha256:f5b77d879412940e (changes whenever the content changes) Timeline: Created: 2026-11-13T03:51:37Z Last changed: 2026-11-13T03:51:37Z Last verified: 2026-11-20T13:39:59Z Next check: 2026-11-21T13:39:59Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of number of reference images | a small set | [1] | 2026-11-20 identification method | Identify each image by order | [1] | 2026-11-20 spatial terms | foreground, background, left, and right | [1] | 2026-11-20 Sources: [1] OpenAI. "Image generation". https://learn.chatgpt.com/docs/image-generation.md Role: primary. Accessed: 2026-11-20T13:39:59Z Quote: "Use a small set of reference images when one image defines the content and" (Supports: number of reference images) Quote: "Identify each image by order and explain how the images relate." (Supports: identification method) Quote: "Use spatial terms such as foreground, background, left, and right when combining elements." (Supports: spatial terms) Snapshot SHA-256: 44bc6988e0557448dc99f8529c04afeae5213af5fb453d631459956600f9b8ff (captured 2026-11-13T03:51:36Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T03:51:37Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:39:59Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:39:59Z Last attempt: 2026-11-20T13:39:59Z Notes and limitations: Extracted automatically from a single official source (section "Use multiple reference images"). Related: https://latestn.com/tool/chatgpt/features/open-annotation-text-range How do I open an annotation from my website for a text range? https://latestn.com/tool/chatgpt/features/open-legal-onboarding-from-chat How do I open the Legal Onboarding plugin from a chat in ChatGPT? https://latestn.com/tool/chatgpt/features/operator-deprecation-chatgpt-agent Is the standalone Operator experience being deprecated now that ChatGPT agent includes a virtual browser? https://latestn.com/tool/chatgpt/features/logged-out-conversation-limit How many conversations can I have in ChatGPT while logged out? https://latestn.com/tool/chatgpt/features/manage-archived-chats How do I manage archived chats in ChatGPT? https://latestn.com/tool/chatgpt/features/maturity-levels-usage-guidance Which ChatGPT and Codex maturity levels are safe to use in production or pilots? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:51:37Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/chatgpt/features/multiple-reference-images/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/chatgpt/features/multiple-reference-images POST: https://latestn.com/dispute/tool/chatgpt/features/multiple-reference-images with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/chatgpt/features/multiple-reference-images?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I use multiple reference images when generating images with ChatGPT? Revision 1, last verified 2026-11-20T13:39:59Z. https://latestn.com/tool/chatgpt/features/multiple-reference-images (accessed 2026-11-21T09:53:49Z). @misc{LatestN_tool_chatgpt_features_multiple_reference_images_r1, title = {How do I use multiple reference images when generating images with ChatGPT?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/chatgpt/features/multiple-reference-images}}, note = {Revision 1; digest sha256:f5b77d879412940e; last verified 2026-11-20T13:39:59Z; accessed 2026-11-21T09:53:49Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/chatgpt/features/multiple-reference-images