Recraft V4 packaging concept art: text-only, WebP on Sume
Use Recraft V4 to explore packaging looks before a shoot: vendor price and design claims, plus Sume's text-only, WebP-only catalog entry.

Is Recraft V4 a good way to explore packaging looks?
It works for concept art, with one limit: on Sume recraft/recraft-v4 is text-to-image only and returns WebP. You describe the pack in words and compare directions; you cannot hand it a dieline or a product photo to edit.
Recraft frames V4 as built for "brand systems and production-ready workflows", with attention to composition, lighting and materials. The vendor page does not mention packaging specifically, so treat packaging as your use of the model, not a claim of it.
What do the vendor pages say?
The fal page prices Recraft V4 at $0.04 per image and lists WebP output. Recraft's own API pricing page lists raster V4 at $0.04 and a separate vector V4 line at $0.08. Neither page documents text rendering, so do not rely on it for legible label copy.
| Item | Vendor | On Sume |
|---|---|---|
| Raster V4 price | $0.04 per image | Read the endpoint pricing line |
| Vector V4 price | $0.08 per image | No vector id in this catalog entry |
| Output format | WebP | WebP only |
| Input | Text prompt | Text only; references are rejected |
| Aspect ratios | Not listed on the pages read | 1:1, 16:9, 9:16, 4:3, 3:4 plus the shared custom-pixel set |
How do I turn concepts into approved art?
Generate a few directions per pack with n up to the catalog range, choose one, and hand the picked WebP to a designer or an edit model. Convert the file first if your pipeline wants PNG or JPEG, as covered in Recraft V4 WebP result: convert before handoff.
If you need a true editable vector, Recraft's separate vector line is the vendor's answer, and the catalog entry here does not include it; see Recraft V4.1 vector SVG API for what is covered.
What does a request look like?
Send the model id, a prompt that names the material and finish, and a ratio. Unsupported parameters such as input_references return a 400, so you find out early.
curl -X POST "https://api.sume.com/v1/images" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "recraft/recraft-v4",
"prompt": "Matte kraft tea box, pine green band, minimal label area, studio light",
"aspect_ratio": "3:4",
"n": 4
}'Sources
Related posts
More in Models
- Cold open with a recurring cast: Gemini Omni Flash with 10 image refs
Gemini Omni Flash 1.1 on Sume takes up to 10 image refs and 3 video refs of 3 s each for a 3 to 10 s vertical cold open with synced audio. Request and limits.
- Reference audio for AI video: which models accept a voice clip
Seedance 2.5, Wan 3.0 and MiniMax H3 take reference audio on Sume; Kling 3, Gemini Omni Flash and the swap rows do not. Limits and the one-reference rule.
- Reference videos in AI video on Sume: Wan, H3, H3 Max and Omni limits
How many reference images, videos and audio files each Sume video model accepts: Wan 10/5/5, H3 9/3/3, Omni 10/3 with 3-second clips, Kling none.
- Omni Flash vs H3 Max for reference-to-video: limits side by side
Gemini Omni Flash 1.1 takes 10 images and 3 short videos; MiniMax H3 Max adds audio refs, 12 files total. Limits, tags and a sample request on Sume.
Written by Sume