Airium
Course · 5 lessons · ~5 minutes

All-rounder Wan 2.7
frames, voiceover, reference video

Alibaba model: frame-to-frame transitions, custom audio track overlay (speech-to-video), reference video generation, and editing of finished clips.

⏱ 4–15 sec🖼 start + end frame🎙 custom audio track🎞 r2v + video edit📺 up to 1080p
Start learning →
1
Lesson 1 · 30 seconds

Choosing a version

In the studio, click the model name at the top, then find on the left Wan — versions on the right:

Airium Studio · model selection · Wan
Wan 2.7NEW
4–15 sec · 1080p · start+end frame · custom audio track · reference video · edit
≈ 22 G-tokens / 5 sec
Wan 2.5
5/10 sec · 1080p · negative prompt + seed · simpler and cheaper
1Wan 2.7 — primary choice: full feature set of the family.
2Wan 2.5 — fast, affordable videos without transition frames.
2
Lesson 2 · 1 minute

Mode and parameters

Wan 2.7 parameters:

parameters panel · Wan 2.7
Mode
From textFrom imageReference videoEdit
Duration
45681015
Format (T2V only) · Quality
16:99:164:3720p1080p
Fine-tuning
negative promptseed🎙 audio file
1Four modes: text, image, video motion transfer, and editing finished video.
2In I2V mode, the format is taken from your image — the format field is only active in T2V.
3Negative prompt and seed — for reproducibility and cleaning up artifacts.
3
Lesson 3 · 1 minute

Frames and your own voiceover

Wan 2.7's standout feature — video synced to YOUR audio track:

"Frames" panel · Wan 2.7
Frame-to-frame transition
First frame
Last frame
Audio track (speech-to-video)
🎙 voice.mp3
a character speaks in your voice — lip-sync automatically
🎙 Upload a voice recording — the character in the image will speak in I2V delivers it with lip-sync. Record a track in the Voiceover tab and connect it here.
🎞 Edit mode: upload a finished clip and describe what to change — Wan will redraw the video following your instructions.
4
Lesson 4 · 1 minute

Writing a prompt

Wan performs most consistently with a clear scene structure.

✕ Weak
«A person walking»
✓ Strong
«A man strides confidently forward along the runway, the camera moves in a circle to the right, shooting his full-body gait, studio light, shallow depth of field»
✅ Negative prompt really works: "blur, artifacts, extra fingers, text" — cleans up the image.
✅ Lock the seed to iterate on the prompt while keeping the same scene character.
5
Lesson 5 · 30 seconds

Generation and result

Hit "Generate" — the task enters the background queue (usually 1–3 minutes). The finished video will appear in your feed and in "My Videos"; tokens for failed generations are refunded automatically.

Real results from Airium Studio — hit play:

Wan · I2V · camera pass«Strides forward, the camera moves in a circle to the right and films the gait»
?
FAQ

FAQ

How to generate video in Wan 2.7 online?
Open Airium Studio, select the Wan 2.7 model in the catalog, set parameters, write your prompt, and click "Generate". Registration takes a minute — new users receive free tokens.

How much does video generation cost in Wan 2.7?
In Airium Studio, generating with Wan 2.7 costs approximately 22 G-tokens / 5 sec. You only pay for successful generations — tokens for failed ones are returned automatically.

What is the maximum video duration in Wan 2.7?
Available durations: 4–15 s (2.7) · 5/10 (2.5). Parameters are set directly in the studio before generation.

Can I use Wan 2.7 without API keys or VPN?
Yes — Airium Studio works in the browser with no API keys, foreign bank cards, or VPN: simply select Wan 2.7 in the catalog and generate online.

Finale

Cheat sheet

ParameterValuesTip
Duration4–15 s (2.7) · 5/10 (2.5)whole seconds
Framesfirst + last (2.7)2.5 supports start frame only
Audiocustom track: t2v background · i2v lip-syncrecord in "Voiceover"
Reference videomotion dynamics transferr2v mode
Editediting a finished videodescribe the changes in a prompt
Controlnegative prompt + seedreproducibility

🗣 Speaking character

Photo + your audio track = a character delivers the text with lip-sync.

🔁 Controlled transition

First and last frame + description of the connection between them.

🧹 Clean image

negative prompt: «blur, artifacts, extra fingers, text».

🎯 Iterations

One seed — change only the prompt wording and compare results.

Start learning →