Describe the frame
Subject, wardrobe, light, lens.
ImageVendor content policy appliesEarly access
文生图 / 首帧
The still before the shot.
Most good clips start as a still. Generate the frame with the model that suits the look — photoreal, editorial, anime — at 1K to 4K, then send it to image-to-video. Each model lists its per-image price and its content policy.
先出一张对的图，再去让它动。每个模型标了每张价格和内容政策。
Text-to-image, first frames
from $0.0045/imagesize
Invite code opens this tool in Chat. No code yet? Join the waitlist — we open the most-requested tools first.
Open in Chat
How it works
Three moves.
Pick a model by look
Seedream for realism, Qwen for text, GPT Image for edits.
Send to video
The still becomes the locked first frame.
You give
Inputs.
- A prompt
- Size / aspect ratio
- Quality tier
You get
Outputs.
- PNG/JPG up to 4K
- Send-to-video in one click
Under the hood
Models behind this tool.
Each model lists its own price and content policy. The spicy route is MiniMax H3; other models follow their vendor’s rules.
FAQ
Short answers.
Which model is uncensored?
Image models here follow their vendor policy; the spicy route is the MiniMax H3 video models. Generate a still within policy, then animate it on H3.
What size should a first frame be?
Match the video aspect ratio at 1080 px or more on the short edge.
Price per image?
From a few cents at the base tier; see each model page.
How do I get access?
Enter an invite code to open the tool in Chat, or join the waitlist from this page. We open seats in batches and prioritise the tools people ask for most.
Related tools