flux-2/max/edit
Precision visual editing tool for consistent, photorealistic brand assets
Qwen Image 3.0 Pro generates a still from a written prompt. These controls shape each Qwen Image 3.0 Pro render.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
prompt* | Yes (*) | String | Example prompt | Up to ~4,500 tokens | Describe subject, setting, style, and any exact text. Quote wording to render it verbatim. |
resolution | No | String | 2k | 1k, 2k | Detail tier: 1k for quick drafts, 2k for maximum detail. |
aspect_ratio | No | String | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4 | Match the frame to your placement. |
enable_prompt_expansion | No | Boolean | true | true, false | Enrich short prompts before generating; turn off when the prompt is already precise. |
seed | No | Integer | -1 | -1 or 0-2147483647 | Fix a seed to reproduce a result; use -1 for fresh variations. |
Qwen Image 3.0 Pro is billed by output tier: $0.038 per 1K image and $0.072 per 2K image. For a batch, total cost is the per-image rate times the number of images.
Precision visual editing tool for consistent, photorealistic brand assets
Create seamless cinematic sequences with smooth framing and stable lighting for coherent story visuals.
Advanced relighting and multi-image fusion tool with fast ControlNet support for detailed, consistent design results.
Generate 4K visuals with precise edits and style control for designers.
Blend and refine visuals with advanced image editing, depth control, and multilingual design precision.
Create consistent visual stories with advanced image editing and multi-scene control.
Qwen Image 3.0 Pro is a production-grade text-to-image model built for polished, detailed results. It handles character art, portraits, fashion and product visuals, and marketing or concept imagery, following prompts closely while keeping textures, lighting, and fine detail clean in a single pass.
Qwen Image 3.0 Pro is tuned for production-grade quality, with stronger detail rendering and prompt adherence aimed at final deliverables. Use it when you want a refined result for commercial or portfolio work rather than a quick draft.
Put the exact wording in quotes inside your prompt so Qwen Image 3.0 Pro renders it verbatim, and describe where each text block should sit. This works well for posters, covers, and product mockups that mix a clear subject with readable typography.
Qwen Image 3.0 Pro offers a 1K or 2K detail tier and aspect ratios of 1:1, 16:9, 9:16, 4:3, and 3:4. Choose 1K for quick exploration and 2K for print- or delivery-ready detail; check the current RunComfy panel for the exact options.
Yes. An optional prompt expansion setting enriches short prompts with extra detail before generating, and a fixed seed lets you reproduce a result. Use -1 for a fresh variation on each run.
Qwen Image 3.0 Pro is billed by output tier: $0.038 per 1K image and $0.072 per 2K image. For a batch, the total is simply the per-image rate times the number of images generated.
Yes. Prototype a prompt in the RunComfy UI, then call the same Qwen Image 3.0 Pro model via the RunComfy HTTP API with identical parameters for automation. You do not need to host or scale the model yourself, and the same inputs produce comparable results.
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.
