# Videm

> Videm is an English-first AI creation service for text-to-image, reference-image transformation, and image-to-video workflows.

## Product

- [Homepage](https://videm.ai/): English-first prompt-based image generator, use cases, pricing entry point, and FAQ.
- [Workflow](https://videm.ai/#how-it-works): Prompt, generate, and iterate.
- [Pricing](https://videm.ai/pricing): Subscriptions and credit packs.
- [Image to video](https://videm.ai/image-to-video): Upload an image, describe motion, and generate a short video with audio-backed results.
- [Image to image](https://videm.ai/image-to-image): Upload a reference image to restyle a photo, change a scene, or create a product variation. Sign-in is required to generate.
- [Face swap](https://videm.ai/face-swap): Upload a source face and target photo, then create an AI face-swap result with usage guidance and FAQ.
- [GPT Image 2.5](https://videm.ai/m/gpt-image-2-5): Create and edit images from text or reference images, compare Flare and Sunburst results, set ratio and resolution, inspect examples, and review credit pricing.
- [Grok Imagine](https://videm.ai/m/grok-imagine): Generate images and videos from text or animate a source image; review examples, settings, workflow guidance, and credit requirements.
- [Grok Imagine (ja)](https://videm.ai/ja/m/grok-imagine): Generate images and videos from text or animate a source image; review examples, settings, workflow guidance, and credit requirements.
- [Grok Imagine (ko)](https://videm.ai/ko/m/grok-imagine): Generate images and videos from text or animate a source image; review examples, settings, workflow guidance, and credit requirements.
- [Grok Imagine (zh-TW)](https://videm.ai/zh-TW/m/grok-imagine): Generate images and videos from text or animate a source image; review examples, settings, workflow guidance, and credit requirements.
- [Nano Banana 2.1](https://videm.ai/m/nano-banana-2-1): Generate and edit images with text or reference images; review output controls, comparison examples, workflow guidance, and credit requirements.
- [Nano Banana 2.1 (ja)](https://videm.ai/ja/m/nano-banana-2-1): Generate and edit images with text or reference images; review output controls, comparison examples, workflow guidance, and credit requirements.
- [Nano Banana 2.1 (ko)](https://videm.ai/ko/m/nano-banana-2-1): Generate and edit images with text or reference images; review output controls, comparison examples, workflow guidance, and credit requirements.
- [Nano Banana 2.1 (zh-TW)](https://videm.ai/zh-TW/m/nano-banana-2-1): Generate and edit images with text or reference images; review output controls, comparison examples, workflow guidance, and credit requirements.
- [Korean homepage](https://videm.ai/ko): Korean-language homepage and generator entry point.
- [Taiwan Traditional Chinese homepage](https://videm.ai/zh-TW): Taiwan Traditional Chinese homepage and generator entry point.
- [Korean pricing](https://videm.ai/ko/pricing): Localized pricing page.
- [Taiwan Traditional Chinese pricing](https://videm.ai/zh-TW/pricing): Localized pricing page.
- [Japanese image to image](https://videm.ai/ja/image-to-image): Japanese AI image transformation page for changing reference-image style, background, and scene.
- [Japanese GPT Image 2.5](https://videm.ai/ja/m/gpt-image-2-5): Japanese GPT Image 2.5 generator with localized workflow guidance, comparisons, output controls, FAQ, and pricing.
- [Korean image to video](https://videm.ai/ko/image-to-video): Korean image-to-video generator page.
- [Korean image to image](https://videm.ai/ko/image-to-image): Korean image-to-image AI generator page.
- [Korean face swap](https://videm.ai/ko/face-swap): Korean face-swap generator page with localized workflow and FAQ.
- [Korean GPT Image 2.5](https://videm.ai/ko/m/gpt-image-2-5): Korean GPT Image 2.5 generator with localized workflow guidance, comparisons, output controls, FAQ, and pricing.
- [Taiwan Traditional Chinese image to video](https://videm.ai/zh-TW/image-to-video): Taiwan Traditional Chinese image-to-video generator page.
- [Taiwan Traditional Chinese image to image](https://videm.ai/zh-TW/image-to-image): Taiwan Traditional Chinese image-to-image AI generator page.
- [Taiwan Traditional Chinese face swap](https://videm.ai/zh-TW/face-swap): Taiwan Traditional Chinese face-swap generator page with localized workflow and FAQ.
- [Taiwan Traditional Chinese GPT Image 2.5](https://videm.ai/zh-TW/m/gpt-image-2-5): Taiwan Traditional Chinese GPT Image 2.5 generator with localized workflow guidance, comparisons, output controls, FAQ, and pricing.

## GPT Image 2.5

- Supports Text to Image and Image to Image workflows in the same workspace.
- Flare is positioned for exploration and faster iteration; Sunburst is positioned for controlled refinement.
- Reference images can guide product identity, people, composition, materials, colors, and focused edits.
- Available output controls include aspect ratio and 1K, 2K, or 4K resolution.
- Published comparison cases cover product editorials, structured explainers, sketches, compositions, and reference-guided changes.
- Generation requires sign-in and uses the credit cost displayed in the workspace before submission.

## Nano Banana 2.1

- Supports text-to-image generation and editing guided by up to 14 reference images.
- Output controls include automatic framing, selectable aspect ratios, and 1K, 2K, or 4K resolution.
- The model requires sign-in and uses credits. Review the displayed cost before generating; the guest free quota does not apply to this model.
- The page includes attributed reference examples, comparisons using the same prompt, and a reference-image workflow. Results depend on the prompt and settings.

## Capabilities And Limits

- Guests can create up to two Videm text-to-image tasks per UTC day.
- New accounts receive five credits once.
- Image-to-image generation requires sign-in. The signed-in seisei-ai model includes up to two free image-to-image tasks per UTC day; after that quota, the standard cost is three credits. Other model costs vary by model and are shown before submission.
- Advanced model selection and account history require sign-in.
- Rights and usage conditions follow the published terms of service.

## Languages And Policies

- English is the primary public language; Japanese, Korean, and Taiwan Traditional Chinese versions are also available.

- [Privacy Policy](https://videm.ai/privacy-policy): Personal data collection, processing, and user rights.
- [Terms of Service](https://videm.ai/terms-of-service): Account rules, acceptable use, and rights and responsibilities for generated content.
- [Refund Policy](https://videm.ai/refund-policy): Refund eligibility and how to contact support about a purchase.
- [Disclaimer](https://videm.ai/disclaimer): Service limitations and responsibility for checking generated content.
- [Contact](https://videm.ai/contact): Account, billing, and generation support.

## Contact

- Support email: support@videm.ai