Jeff Harris
@jeffintime
Followers
4K
Following
9K
Media
145
Statuses
1K
the malleability of minds. API product @openai
Oakland
Joined January 2008
RT @edwinarbus: High fidelity image editing is now in the OpenAI API and ChatGPT!. Here's a quick demo I made that focuses on editing faces….
0
29
0
Imagegen high fidelity inputs are ideal for classic image editing tasks.✔️ Remove clutter, people, distractions.🔄 Swap objects.🎨 Change colors, textures, clothing.🌤️ Global tweaks: lighting, weather, time of day
We've improved image generation in the API. Editing with faces, logos, and fine-grained details is now much higher fidelity with features preserved. 🔍. Edit specific objects, create marketing assets with your logo, or adjust facial expressions, poses, and outfits on people.
0
0
6
We’ve made 13 price cuts since 2023 (same or better models) ✅.Plus batch + prompt caching ✅. 80% cuts? Just twice:.- gpt-3.5-turbo.- text-embedding-3-small. Thrilled to see what you ship with today’s o3 drop.
we dropped the price of o3 by 80%!!. excited to see what people will do with it now. think you'll also be happy with o3-pro pricing for the performance :).
1
0
27
regularly blows my mind how easy it is to create images using up-to-date world knowledge. Include `image_generation` and `web_search_preview` as tools in Responses then try a prompt like."Draw me a picture of downtown Seattle that shows the current time PDT and the weather".
ICYMI: Image generation is now available as a Responses API tool—and includes new capabilities:. 🌊 Streaming: see partial images as they load .⤴️ Multi-turn edits: high fidelity edits with cache savings .🌐 Combine with tools like MCP or web search for generations using live
0
1
5
when you leave background, quality, and size blank—the image API inspects the user's prompt and intelligently picks the best params. 🚢micro-ship: the response now echoes those choices, so you get smart defaults and full visibility
0
0
4
Just updated our caching guide to explain how routing works. We route prompts by org, hashing the first ~256 tokens, and spillover to more machines ~15 RPM. If you've got many prompts with long shared prefixes, the user param can improve request bucketing and boost cache hits
6
12
146
just use the partial_images parameter in the Responses API tool.
2
0
15
gpt-image-1 works hard and takes time. now you can stream incremental updates from the API, letting users see the magic as it's happening
5
0
51
gpt-image-1 is live in the Responses API!. Best part: the stateful API supports precise, multi-turn image edits. no more quality loss from repeated pixel conversions.
2
0
12
microship: OAI transcription API now supports specifying `chunking_strategy` . Use this to preprocess audio by removing silence. Improves recognition accuracy and reduces chances of getting a truncated transcript. Lots of 🎛️ if you want to tune or just set to `auto`
3
2
12
gpt-image-1 magic ✨.
0
0
7
our new image model comes in a few quality levels. The low-quality option is super affordable—still gorgeous, great at instruction following, but less precise on fine details like text or remixing images. some LQ images.
1
0
6
RT @figma: Two AI updates rolling out starting today to Figma Design now using OpenAI’s gpt-image-1. → Edit image (brand new feature!).→ Ma….
0
96
0
RT @OpenAIDevs: Image gen is now available in the API!. We’re launching gpt-image-1, making ChatGPT’s powerful image generation capabilitie….
0
735
0