Character-based image and video generation
Artflow positions the product as an AI photography studio for creating character-based images and videos, with the ability to place a person into different scenes, outfits, and roles.
Artflow is an AI photography studio that generates character-led images and videos from uploaded photos, templates, and prompts. The product is centered on creating a reusable identity and placing that person into different scenes, outfits, and visual styles.
The site organizes the workflow around Actor Builder, Image Studio, and supporting tutorial content. Actor Builder trains a person from a set of uploaded images, while Image Studio and related edit tools are used to produce new scenes, refine appearance, and adapt the result to different use cases.
Artflow positions the product as an AI photography studio for creating character-based images and videos, with the ability to place a person into different scenes, outfits, and roles.
The Image Studio page highlights template-driven creation across categories such as professional, lifestyle, travel, fantasy, romantic, and celebration, giving users a starting point for different output styles.
Actor Builder lets users upload photos of one person to train an actor, then reuse that identity in Image Studio for new generated scenes.
The Resources pages describe edit workflows such as Edit Instruct, Background Swap, Wardrobe & Style, Mood & Lighting, Scene Remix, and prompt guidance for image generation.
The pricing page lists output and workflow features including no-watermark images, background removal, upscale, bulk download, PNG download, video model access, and unlimited Spark generation on higher tiers.
The pricing page also shows plan-based controls such as license type, moderation level, and concurrent generation limits.
Train a reusable actor from a set of photos, then generate that person in different locations, outfits, and scene setups without starting from scratch each time.
Use the template library to create polished portraits and themed images for categories such as professional headshots, travel, fantasy, celebration, and lifestyle content.
Apply edit workflows such as background swap, wardrobe and style changes, mood and lighting adjustments, or scene remixing to refine an existing image direction.
Create images or videos for a project with plan-appropriate licensing, background removal, upscale, and download options for delivery or post-processing.
Follow the resource guides to learn prompt writing, image workflows, and tutorial-based setup before producing your own outputs.
Yes. The pricing page says generated images and videos can be used in projects, with licensing depending on the plan. Basic uses CC BY-NC 2.0, Starter uses CC BY 4.0 with attribution, and Pro includes commercial use without attribution.
The pricing page says credits reset and are topped up every month based on the plan you are on.
Yes. The pricing page says you can cancel at any time and keep premium features until the end of the billing period.
Yes. The pricing page says you can upgrade from your account settings, with billing and credits recalculated and prorated. For downgrades, Artflow says you need to cancel first and then subscribe to a different plan at the start of a new billing period.
The pricing page says API access is available by request through a form, and the team will follow up.
Wallieは、画面を見てチャットを聞き、設定したペルソナでライブ解説を生成するオープンソースAI streamer。自分のキーでローカル実行でき、顔出しなし配信や自律配信、リアルタイム反応に最適です。
PixelForgeは1枚の写真から、4×4シート、透過フレーム、方向別ストリップ、ループ再生の歩行GIFを備えたゲーム向け2Dキャラクタースプライトパックを生成します。Godot、Unity、Phaser、GameMaker、Webゲームにそのまま使える設計です。
Mixels.ai is a browser-based AI pixel art generator for creating 8-bit characters, sprites, avatars, and photo-to-pixel conversions. It is designed for users who want grid-aligned retro artwork without installing software.
FashionLabs is an AI image generation and editing tool for apparel and product photography. It helps e-commerce businesses create model images, product display images, and related commercial visuals with AI.
HeyGen Avatar Vは、15秒のWebカメラ動画からデジタルツインを生成し、一貫したアイデンティティ、自然な動き、音声で話すアバター動画を作成します。
魔珐星云は、開発者向けの3D具身智能デジタルヒューマン開放プラットフォーム。リアルタイム駆動、動画生成、音声合成に対応し、テキストを対話型デジタルヒューマン体験へ素早く変換。API連携も可能です。