minimaxiH3 Get access
MidjourneyImage-to-videoVendor content policy applies

Youchuan V8.1 Image-to-Video

Youchuan V8.1 animates an input image into four 5-second videos at 480p or 720p.

$0.13per secondStarting price at the base resolution and quality tier.
$1.03Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A celestial maiden with snow-white hair embraced by golden-yellow parrots, serene expression, birds whispering around her, delicate ivory lace gown, enchanted fairytale atmosphere, golden morning light filtering through …”

What it does

Youchuan V8.1 Image-to-Video, in practice.

> About Youchuan (悠船): "Youchuan V8.1" is Midjourney's V8.1 model delivered through Youchuan (悠船), Midjourney's officially authorized platform in China — self-branded *"Midjourney 中国实验室" (Midjourney China Lab)* and operated by Xiaochuan Creative (Shanghai) Network Technology Co., Ltd. (小船创意). Youchuan is a legitimate, licensed distributor of Midjourney's models (not a third-party clone): it offers the same Midjourney technology, localized for the Chinese market with priority access to new model versions. Youchuan V8.1 is the latest iteration of Midjourney's image-synthesis model. This README covers the two core generation endpoints: It belongs to a larger Youchuan V8.1 family on this platfor

  • Native 2K HD output without a separate upscaler: V8.1 generates directly at 2048px resolution, eliminating the dedicated upscaling step required by earlier versions. HD renders take roughly 1.33 GPU-minutes and standard-definition renders under 1 GPU-minute, with HD running approximately 3× faster and cheaper than in V8.
  • ~4–5× faster generation: The GPU-native PyTorch rewrite delivers an estimated four-to-fivefold speedup in generation time over previous Midjourney versions (a Midjourney-stated figure, not an independent benchmark), improving iteration speed for creative workflows.
  • Improved text rendering: V8.1 renders in-image text more reliably, with quoted strings in prompts used to specify the intended text — narrowing a long-standing weakness relative to text-specialized competitors.
  • Stronger prompt-following: The model adheres more closely to prompt instructions, improving controllability and reducing the prompt-engineering effort needed to achieve a target composition.
  • Restored image conditioning: Image prompts and image weights — absent in the V8.0 alpha — returned in V8.1, alongside backward compatibility with V7 style references (srefs), moodboards, and personalization profiles. (Image-driven generation is offered here as the dedicated `youchuan/v8.1/image-to-image` and `blend` models.)
  • Workflow tooling: V8.1 ships with a Prompt Shortener and an updated `/describe` command, and its aesthetic has been re-tuned "in the spirit of V7" to preserve the look users prefer.

Run Youchuan V8.1 Image-to-Video

from $0.13/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
resolution
motion
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
imageFirst-frame image to animate. A publicly reachable https image URL (or upload). The generated video keeps the input image's aspect ratio. Each task returns 4 five-second videos.
promptOptional text describing the motion / scene for the generated video.default gentle camera push in, cinematic
resolutionOutput resolution. 720p costs 3x of 480p.480p 720p
motionAmount of motion in the generated video.low high

Sample prompt

The prompt behind the sample.

A celestial maiden with snow-white hair embraced by golden-yellow parrots, serene expression, birds whispering around her, delicate ivory lace gown, enchanted fairytale atmosphere, golden morning light filtering through mist, subtle feather movement, flowing hair, cinematic dolly-in shot, dreamy bokeh, soft focus, emotional storytelling, fantasy realism, Denis Villeneuve-inspired cinematography, volumetric sunlight, ultra detailed, magical realism, masterpiece Camera Movement: Slow orbit camera, gentle handheld drift, extreme close-up on the birds and girl's face, feathers moving naturally, c
resolution: 480penable_base64_output: motion: low

FAQ

Short answers.

How much does Youchuan V8.1 Image-to-Video cost?

Pricing starts at $0.13 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $1.03. Usage is billed per request from your balance — no subscription.

Does Youchuan V8.1 Image-to-Video run uncensored here?

No. Midjourney applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Youchuan V8.1 Image-to-Video for everything else it does well.

What does Youchuan V8.1 Image-to-Video take as input?

It is a image-to-video model. Youchuan V8.1 animates an input image into four 5-second videos at 480p or 720p.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Youchuan V8.1 Image-to-Video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models