Compose a product hero
Specify the camera angle, light and space around the product. Leave room for the headline or layout you will add later.
OpenAI Image generation & editing
Generate and edit images with GPT Image 2 in Riverflow. Guide a product composition with a detailed brief and reference photos.
Open Riverflow
The example
A listening room in walnut, orange and cobalt.
Photograph an art-directed listening-room still life for an independent audio brand, landscape 4:3. A beautiful compact orange turntable with a smoked transparent lid partly raised sits on a dark walnut low table. One black vinyl record plays; its cream centre label reads exactly SIDE A in neat small black letters. At the right is a single compact walnut speaker with a circular linen grille. A sharply folded cobalt-blue record sleeve leans against the table, no printing. Low golden evening sunlight through venetian blinds creates diagonal shadows across warm off-white plaster. Close, low three-quarter camera angle, 65mm lens, expensive editorial interiors photography. Rich but restrained colours: burnt orange, walnut, cobalt and cream. Authentic materials, precise turntable geometry, realistic tiny dust and grain. No people, no floating objects, no giant text, no graphic overlay. Let the left upper third remain calm and airy; keep the entire turntable and speaker within frame.
Select GPT Image 2 after opening the image tool.
GPT Image 2 is OpenAI’s image generation and editing model, and the predecessor to GPT Image 2.5. It turns written instructions and reference images into new compositions or edits, with support for combining multiple image references. Riverflow offers it at High quality for work such as product imagery, campaign concepts and image revisions.
Choose GPT Image 2 in Riverflow’s image tool, add your brief and references, then review the settings and credit cost before generating.
Available settings depend on the model and workflow.
Plans and credits| Model | 1K | 2K | 4K |
|---|---|---|---|
| GPT Image 2 High | 18 credits | 18 credits | 40 credits |
One image uses the amount shown. Four 2K images use four times the 2K cost. Image edits can use a different rate; check the quote in the editor. Your complete quote appears before generation.
Specify the camera angle, light and space around the product. Leave room for the headline or layout you will add later.
Use one image for the product and another for the setting or colour palette. Explain each reference’s role in the finished shot.
Make a targeted change to a source image. Compare the full result with the original, including the details you asked to keep.
Models, inputs and getting started.
GPT Image 2 is OpenAI’s image generation and editing model, and the predecessor to GPT Image 2.5. It turns written instructions and reference images into new compositions or edits, with support for combining multiple image references. Riverflow offers it at High quality for work such as product imagery, campaign concepts and image revisions.
GPT Image 2 is the earlier generation. Riverflow’s GPT Image 2.5 option uses Sunburst, a variant focused on higher-precision editing rather than creative exploration and divergent results. Both support text-to-image generation and multi-reference editing at High quality. GPT Image 2.5 also supports native transparency in the image-editing workflow.
Sign in to Riverflow, open the image creation tool and choose GPT Image 2 from the model picker. Add your brief and any required references, then review the available settings and credit cost before generating.
GPT Image 2 High costs 18 credits per 1K image, 18 credits per 2K image and 40 credits per 4K image in Riverflow’s image generator. Generating multiple images multiplies that cost. Credits are included in Riverflow subscriptions; see the pricing page for plan allowances.
Bring your brief. Choose your model. Start creating.