flux-2/flash/edit
Accelerate visual editing with dynamic precision and open-weight adaptability for brand-consistent designs.
Wan 2.7 text-to-image on RunComfy turns English or Chinese prompts into still images. The model emphasizes prompt understanding and detailed output. Maximum resolution and hard limits follow the current RunComfy deployment for this model.
Each successful run returns one to five images per request in the images array, optional generated_text from the model, and a seed in the response.
image_size presets: square_hd, square, portrait and landscape 4:3 and 16:9. A {width, height} object may be supported in advanced integrations.max_images 1–5 for variations in one job.seed in [0, 2147483647].enable_safety_checker moderates input and output (default on).| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes | string | — | — | Main scene, style, and composition. |
| negative_prompt | No | string | "" | max 500 chars | Content to avoid. |
| image_size | No | string | square_hd | enum presets | Output aspect/size preset. |
| max_images | No | integer | 1 | 1–5 | How many images to generate. |
| seed | No | integer | — | 0–2147483647 | Reproducibility. |
| enable_safety_checker | No | boolean | true | on / off | Input/output moderation. |
| Billing | Rate |
|---|---|
| Per generated image | $0.03 |
Charges scale with the number of images (max_images) in a single request.
negative_prompt only for concrete things you want suppressed.max_images greater than 1 when exploring variations; keep seed fixed to compare prompt edits.Accelerate visual editing with dynamic precision and open-weight adaptability for brand-consistent designs.
Produce high-fidelity visuals with clear text, fast generation, and professional design control.
Generate images from text prompts with Wan 2.5 Preview.
Redefine design with striking visuals and bold typography.
Generate and edit images from prompts and photos with OpenAI GPT-4o Image.
8-step Turbo model enabling rapid, high-quality visual edits for creators
RunComfy hosts the Wan 2.7 text-to-image integration for Alibaba’s model family. The playground sends the documented keys—prompt, negative_prompt, image_size, max_images, seed, and enable_safety_checker—to the inference route configured for this tool.
RunComfy pricing is $0.03 per generated image. If you set max_images greater than 1, the total scales with how many images the job returns.
Yes. You can write prompts in Chinese or English on this RunComfy playground.
max_images must be an integer from 1 to 5 for this model.
Both use the same parameter names. Standard text-to-image is priced lower and suits drafts and fast iteration; Pro targets higher-fidelity output and a higher per-image price. Pick standard for exploration and Pro when you need final hero frames.
This playground is set up for string presets so inputs map cleanly through the default integration. A custom {width, height} object may work in advanced or API-only setups—confirm in your RunComfy workspace settings before you rely on arbitrary dimensions.
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.
