通用文生图视频
LoomLoom official根据画面描述批量生成图片，再进一步生成短视频，适合通用视觉内容生产场景。
Updated Jul 21, 2026Version v3Output type 图片 + 视频
Value
Decide whether this SkillBot fits your task
Best-fit scenarios
创意概念图、角色场景图、短视频分镜、社媒素材批量生产
Inputs and final outputs
Input
What you provide
每行填写一段画面描述，并指定图片比例、视频比例和视频时长；每一行独立生成一组图片和视频结果。
| Input field | Type | Requirement | Description |
|---|---|---|---|
| 画面描述 | Text | Required | 填写一段普通文本。 |
| 视觉风格要求 | Text | Optional | 填写一段普通文本。 |
| 参考图片url | image_url | Optional | 仅支持公网 http/https 图片链接。 |
| 图片比例 | Options | Required | 只能填写预定义选项中的一个值。Allowed values: 1:1, 4:5, 16:9, 9:16 |
| 图片生成模型（可选） | Options | Optional | 只能填写预定义选项中的一个值。Allowed values: ali/qwen-image-3.0, ali/qwen-image-edit-plus, ali/qwen-image-plus, ali/wan-2.2-t2i-lora, ali/wan2.5-i2i-preview, ali/wan2.5-t2i-preview, ali/z-image-turbo, black-forest-labs/flux-1.1-pro, black-forest-labs/flux-1.1-pro-ultra, black-forest-labs/flux-1.1-pro-ultra-finetuned, black-forest-labs/flux-dev-lora, black-forest-labs/flux-kontext-dev, black-forest-labs/flux-kontext-dev-lora, black-forest-labs/flux-kontext-max, black-forest-labs/flux-kontext-pro, bytedance/doubao-seededit-3-0-i2i, bytedance/doubao-seedream-3.0-t2i, bytedance/doubao-seedream-4.0, bytedance/doubao-seedream-4.5, bytedance/doubao-seedream-5-0-lite, bytedance/doubao-seedream-5-0-pro, bytedance/image_enhance, bytedance/image_upscale, bytedance/jimeng_i2i_v30, bytedance/jimeng_t2i_v30, bytedance/jimeng_t2i_v31, bytedance/jimeng_v40, google/gemini-2.5-flash-image, google/gemini-3-pro-image, google/gemini-3.1-flash-image, openai/gpt-image-1, openai/gpt-image-1-mini, openai/gpt-image-1.5, openai/gpt-image-2, openai/gpt-image-2.5-flare, vidu/viduq1-image |
| 视频比例 | Options | Required | 只能填写预定义选项中的一个值。Allowed values: 16:9, 9:16 |
| 视频时长（秒） | Options | Required | 只能填写预定义选项中的一个值。Allowed values: 4, 6, 8 |
| 是否生成声音 | Options | Required | 只能填写预定义选项中的一个值。Allowed values: false, true |
| 视频生成模型（可选） | Options | Optional | 只能填写预定义选项中的一个值。Allowed values: ali/happyhorse-1.0-i2v, ali/happyhorse-1.0-r2v, ali/happyhorse-1.0-t2v, ali/happyhorse-1.0-video-edit, ali/happyhorse-1.1-i2v, ali/happyhorse-1.1-r2v, ali/happyhorse-1.1-t2v, ali/wan-2.2-i2v-fast-lora, ali/wan-2.2-t2v-fast-lora, ali/wan2.2-animate-mix, ali/wan2.2-animate-move, ali/wan2.2-i2v-flash, ali/wan2.2-i2v-plus, ali/wan2.2-kf2v-flash, ali/wan2.2-s2v, ali/wan2.2-t2v-plus, ali/wan2.5-i2v-preview, ali/wan2.5-t2v-preview, ali/wan2.6-i2v, ali/wan2.6-r2v, ali/wan2.7-i2v, ali/wan2.7-r2v, ali/wan3.0-video, ali/wan3.0-video-prime, bytedance/doubao-seedance-1.0-lite-i2v, bytedance/doubao-seedance-1.0-lite-t2v, bytedance/doubao-seedance-1.0-pro, bytedance/doubao-seedance-1.5-pro, bytedance/doubao-seedance-2-0, bytedance/doubao-seedance-2-0-fast, bytedance/doubao-seedance-2-5, bytedance/jimeng_i2v_first_tail_v30, bytedance/jimeng_i2v_first_v30, bytedance/jimeng_i2v_first_v30_1080, bytedance/jimeng_i2v_recamera_v30, bytedance/jimeng_t2v_v30, bytedance/jimeng_t2v_v30_1080p, bytedance/jimeng_ti2v_v30_pro, google/gemini-omni-1.1-flash-preview, google/gemini-omni-flash-preview, google/veo3, google/veo3.1-fast-preview, google/veo3.1-preview, kling/kling-3.0, kling/kling-3.0-turbo, kling/kling-v1-6, kling/kling-v2, kling/kling-v2-1, kling/kling-v2-1-master, kling/kling-v2-5-turbo, kling/kling-v2-6, kling/lipsync, minimax/i2v-01-director, minimax/i2v-01-live, minimax/minimax-h3, minimax/s2v-01, minimax/t2v-01-director, openai/sora2, runway/gen3a_turbo, runway/gen4_aleph, runway/gen4_turbo, vidu/vidu1.5, vidu/vidu2.0, vidu/viduq1, vidu/viduq2-turbo, vidu/viduq3-pro |
Output
What you receive
No output details
The creator has not yet provided output content or execution result details for this Skill.
Instructions
- 每一行表示一个任务。
Examples
- 图片比例
- 4:5
- 是否生成声音
- false
- 画面描述
- 一盏未来感桌面台灯，玻璃与金属材质，放在极简工作台上，画面干净克制，突出轮廓光和材质细节
- 视觉风格要求
- 极简棚拍，纯净浅色背景，柔和顶光与轮廓补光
- 视频时长（秒）
- 4
- 视频比例
- 9:16
Trust and update history
Current versionv3
Downloads4
Calls8
| Date | Version | Update summary |
|---|---|---|
| Jul 21, 2026 | v3 | Production sync after CogFoundry row-per-task validation |
| May 28, 2026 | v2 | v0.2.0 compatibility: bind reference_image_url to image reference port |
| Apr 20, 2026 | v1 | official template import |