Create consistent visual stories with advanced image editing and multi-scene control.
Black Forest Labs' FLUX 3 Image Klein writes one still from a text prompt at 768, 1K, 1.5K, 2K, or 4K.
Trading a separate enlarge pass for a native size tier, FLUX 3 Image Klein helps poster, product, and catalog teams start from a short brief.
For developers, FLUX 3 Image Klein on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Product Stills | Poster Frames | Catalog Crops
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
prompt* | Yes (*) | string | Example line | Text | The scene. Negative prompts are not a separate field. |
aspect_ratio | No | string | 1:1 | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21, auto | Frame shape. auto follows the prompt, then 1:1. |
resolution | No | string | 1k | 768sq, 1k, 1.5k, 2k, 4k | Size tier. This is the only setting that changes the price. |
output_format | No | string | jpeg | jpeg, png | File type. |
steps | No | integer | 16 | 1-16 | Sampling steps. The price does not change. |
safety_tolerance | No | integer | 2 | 0-4 | 0 is the strictest filter. |
seed | No | integer | Empty | 0-4294967295 | Repeat a result when the other settings stay the same. |
One image per request. Aspect ratio, steps, seed, file type, and safety tolerance do not add a fee. Text and edit use the same rates.
| Resolution | Price per image |
|---|---|
| 768 | $0.007 |
| 1K | $0.008 |
| 1.5K | $0.009 |
| 2K | $0.013 |
| 4K | $0.035 |
Create consistent visual stories with advanced image editing and multi-scene control.
Text-to-image and image editing with layout and layer control
Fast instruction-based editing of up to 16 images, with mask support.
Create realistic visuals from prompts with precise multilingual text control and balanced layouts.
Qwen Image 2.1: unified generation, edit, and transparency
Generate detailed multilingual visuals with 4K clarity and creative control.
FLUX 3 Image Klein writes one still from a text prompt. It is aimed at product stills, poster frames, and catalog crops where the size tier is chosen up front, from 768 through 4K.
FLUX 3 Image Klein offers 768, 1K, 1.5K, 2K, and 4K. 1K is the default. 768 is about a 768 square, 1K is about 1 megapixel, 1.5K about 2, 2K about 4, and 4K about 16. The returned pixel size still depends on the aspect ratio.
Describe the subject, the place, and the light in one paragraph. FLUX 3 Image Klein has no separate negative prompt, so say what you want in the frame. Short quoted words are more reliable than a long line of type.
Yes. A box list can sit inside the same prompt, on a 0 to 1000 grid, when a region should land in a set part of the frame. The box is not a separate control on the page.
Each request returns one image. Aspect choices include the common photo ratios plus 9:21 and auto. Steps run from 1 to 16, and the seed runs from 0 to 4294967295. File types are JPEG and PNG.
4K can take several minutes. Smaller tiers return sooner. Steps also affect wait time, and they do not change the price.
Yes. Prototype FLUX 3 Image Klein in the RunComfy model UI, then send the same prompt and settings to the HTTP API. That path does not add a separate hosting step, and it does not promise a fixed response time.
FLUX 3 Image Klein costs $0.007 at 768, $0.008 at 1K, $0.009 at 1.5K, $0.013 at 2K, and $0.035 at 4K. Aspect ratio, steps, seed, and file type do not add a fee. New accounts usually start with a trial balance, and each run spends usd or credits.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.





