Skip to main content
MeiGen lets you generate images and videos using multiple AI models from a unified interface. On desktop, open the generation sidebar from the floating dock; on mobile, tap Generate in the bottom dock to open the generation sheet. Both surfaces offer the same models, reference images, @ mentions, prompt enhancement, AI edit, and Storyboard — this guide applies to both unless a section says otherwise.

​
Model Selector

At the top of the generation sidebar, the model selector dropdown lets you choose which AI model to use. Each option shows:
  • Provider icon — visual indicator of the model provider (Google, ByteDance, Midjourney, etc.)
  • Model name — the display name of the model
  • Credit cost — how many credits this model uses per generation
Selecting a different model automatically updates the available aspect ratios, resolution options, and advanced settings to match that model’s capabilities.

Model Comparison

Compare available models — features, pricing, strengths, and limitations

​
Skills

Need a guided, multi-step workflow instead of a single prompt? Skills turns one product photo into a full set of e-commerce visuals — product detail pages, white-background shots, marketing posters — through a step-by-step wizard.

Skills

Guided AI workflows for product photography and marketing visuals

​
Prompt Editor

​
Writing Effective Prompts

  • Be specific — describe composition, lighting, colors, textures, and perspective for the best results
  • Short prompts work too — use the Enhance button to expand brief descriptions into detailed prompts automatically
  • Language — most models accept English prompts. Midjourney V8.2 will auto-translate non-English prompts to English

​
Variable Tags

Some prompts from the gallery contain blue [placeholder] tags — for example, [style], [subject], or [color palette]. These are editable template variables. Click any blue tag to select it, then type your replacement text. This makes it easy to create variations of a prompt without rewriting the whole thing.

​
@ Mentions

When you have reference images — or, on video models, reference videos and audio — uploaded, you can mention a specific item inline in your prompt:
  1. Type @ in the prompt editor
  2. A popup lists everything you have uploaded. Images show a thumbnail; videos and audio show a video or audio icon only, with no preview frame
  3. Select an item to insert a mention tag (@image1, @image2, @video1, @audio1)
  4. Write instructions around the mentions: “Use @image1 as the background scenery, continue the camera move from @video1, and match the rhythm of @audio1”
Numbering runs per kind, following the order of the items in each module — @video2 is the second reference video, not the second item overall. Inline chips look the same as the popup rows, icon-only for video and audio. Remove an item and the remaining tags renumber themselves; a tag whose item is gone is marked stale so you can fix it before generating. This gives you precise control over how each reference influences the generation.

​
Characters

Create a character once and reference it across generations, so the same figure stays consistent from image to image — and into video.
  1. Click the Characters button above the prompt editor (available in both the image and video sidebars)
  2. In Create Character, give it a name and add 1–4 images — upload them, or pick from your recent creations
  3. Back in the prompt, type @ and select the character: “@Mia standing in a neon-lit alley, cinematic lighting”
You don’t need to attach the character’s images as reference images again — selecting it in the prompt is enough. Rename or delete characters under My Characters; deleting one breaks the prompts that reference it.
Best results: give the character one vertical full-body shot plus one neutral face close-up of the same character.
Only AI-generated or virtual characters are allowed. Images that resemble a real person are rejected by content review.
Limits — there is a cap on how many characters an account can keep, and on how many you can create per day. The dialog tells you when you reach it; delete unused characters under My Characters to free up room.Availability — image models that accept reference images (all except Flux 3 Image Klein), plus Seedance 2.5 and Seedance 2.0 for video. Selecting a character on a text-only model returns an error.If you submit a work that mentions a character to the public gallery, that character’s main image becomes publicly visible alongside it — the publish dialog asks you to confirm first.

​
# Color Picker

When you need to specify an exact color for an object in your prompt, pick one from the palette:
  1. Type # in the prompt editor
  2. A palette appears with common colors and curated hues grouped by shade
  3. Click any swatch to insert a color tag (e.g., #dc143c)
  4. Write instructions around the color: “A t-shirt in #dc143c paired with #f5f5dc pants”
Colors are submitted to the model as hex values — more precise than describing “deep red” or “beige” in words.

​
Translate Button

Click the translate icon (top right of the prompt editor) to translate your prompt into English. This is useful when writing prompts in another language, as most models produce the best results with English input.

​
Prompt Enhancement

Click the Enhance Prompt button to automatically enhance your prompt based on the selected model:
  • Polish mode (most models) — preserves intent, adds visual details like composition, lighting, and materials
  • Expand mode (Midjourney V8.2) — expands into Midjourney-optimized language; non-English prompts are auto-translated
Enhancement works best on brief prompts (under 30 words). Skip it for prompts that already have detailed visual descriptions — the AI may over-process them.

​
AI Edit

Give the AI a one-line instruction to make a precise change to your current prompt — not a full rewrite.
  1. Click AI Edit above the prompt editor
  2. Describe the change, e.g. “make the lighting warmer” or “change the cat to a dog”
  3. The AI applies just that change and leaves the rest of the prompt untouched
AI Edit shares a daily quota with Prompt Enhancement and Storyboard, and doesn’t spend generation credits.

​
Keyboard Shortcuts

​
Reference Images

Upload reference images as visual context to guide the AI’s output — for style matching, composition guidance, or subject reference.
  • Upload methods — drag-and-drop files onto the reference area, or click to browse
  • Supported formats — JPG, PNG, WebP
  • Auto-compression — images are automatically compressed to max 2MB / 2048px before upload
  • Maximum source dimensions — an image whose width or height exceeds 8000 pixels is rejected before upload, with a message asking you to resize it. Everyday files stay well clear of this: a 4K photo is 3840px on its long edge, and an A4 scan at 300dpi is 2480×3508. Only print-scale source files (large-format banners, poster artwork at full print resolution) run into it — scale those down before uploading
  • Thumbnail grid — uploaded images appear as thumbnails with an × button to remove each one
  • Per-model limits — the maximum number of reference images varies by model (0–16; GPT Image 2.5 and GPT Image 2 each accept up to 16). Models that don’t support references (currently Flux 3 Image Klein) hide this section entirely.
See the Models page for the exact reference image limit of each model.
You don’t need to download images first. Drag any gallery card directly into the reference image area — the image URL is used automatically.
Combine gallery references with @ mentions for powerful multi-reference workflows. For example, drag two gallery cards as references, then write: “Combine the composition of @image1 with the color palette of @image2.”

​
Reference Types (Midjourney V8.2)

When using Midjourney V8.2 with a reference image, a dropdown appears to choose how the reference is interpreted:

​
When to Use Reference Images

Some prompts work best — or only make sense — with a reference image attached. MeiGen automatically detects keywords like “reference image” or “uploaded image” in your prompt and shows a hint if no reference is uploaded. Common patterns that need reference images:
If your prompt describes transforming, redrawing, or referencing a specific image, always upload that image as a reference first. Without it, the AI will generate something unrelated to your intent.

​
Reference Video & Audio

On Seedance 2.5 and Seedance 2.0, the video sidebar’s Reference video & audio module accepts several clips at once — videos to continue or condition on, audio to score or style the result.
  • Upload methods — drag files onto the module, or click + to browse
  • Supported formats — MP4 and MOV for video, WAV and MP3 for audio
  • Thumbnail grid — items appear as a grid on the left, exactly like reference images: a video shows a frame thumbnail, an audio clip shows an audio tile. Each has an × button to remove it. The module title disappears as soon as the first item is added, and the + button stays visible until you reach the model’s cap
  • Per-model counts and totals — Seedance 2.5 takes up to 10 videos (2–30s each, 30s in total) and up to 10 audio clips (2–30s each, 30s in total). Seedance 2.0 takes up to 3 videos (2–15s each, 15s in total) and up to 3 audio clips (2–15s each, 15s in total)
  • Size limits — video is up to 200MB per clip on Seedance 2.5 and 50MB on Seedance 2.0; audio is up to 15MB per clip on both
  • Seedance 2.0 needs something visual — reference audio on 2.0 only works alongside at least one reference image (a saved character counts) or one reference video. Seedance 2.5 accepts audio on its own
  • @ mentions — every uploaded video and audio clip can be mentioned in the prompt as @video1 / @audio1, shown with an icon only
  • Audio is free — reference audio never changes the credit cost; only the videos do
Items the currently selected model or settings cannot use stay in the module, greyed out and labelled “Not used by the current model settings” — switch back and they come straight into play again. See the Models page for each model’s exact counts and totals.

​
Generation Options

​
Count

Choose how many images to generate per request (1–4).
  • Free users — limited to 1 image per request. A lock icon appears on the + button.
  • Paid users — can generate up to 4 images in parallel per request.

​
Aspect Ratio

The default is Auto — no need to pick manually, a suitable ratio is chosen for you. Drop into the dropdown to pick a specific ratio when you want precise control.
Not all models support all ratios. The selector automatically filters to show only ratios supported by the current model. See the Models page for each model’s supported ratios.

​
Resolution

The resolution options come from the model you picked — the selector only offers what that model supports:
The highest option of each model is paid-only and shows a lock icon for free users. On a 1K / 2K model that means 2K is locked; on a 2K / 4K model it’s 4K; on a 2K / 3K model it’s 3K. The same rule applies to 4k on video (Seedance 2.0 Pro and Veo 3.1).

​
GPT Image 2.5 Quality and Variant

Choose GPT Image 2.5 when it is available in your model list. It has five quality levels: Standard, Medium, High, Extra High, Max. The API values are low, medium, high, xhigh, and max.
  • Sunburst — quality priority: the default variant, for generation and editing where preserving details matters.
  • Flare — speed priority: an alternative when turnaround matters. It accepts the same reference images and quality settings.
Both variants cost the same. References and aspect ratio do not add credits; the price depends on resolution and quality. An attached reference does not switch the variant automatically. Describe whether each reference provides a subject, a style, or the image to edit, and specify what must stay unchanged. Configured starting settings are 2K Standard / 6 credits on desktop and 1K Standard / 4 credits on mobile, both with Sunburst. The current platform default is the model marked is_default in List Models. See the full price table before choosing a higher quality. GPT Image 2 retains its own three quality levels and prices. Retrying a 2.5 generation restores its resolution, quality, and variant; changing the model may reset unsupported options.

​
Midjourney V8.2 Advanced Options

When using Midjourney V8.2, the Advanced Options button lets you tune extra generation parameters. Most users can leave everything at defaults.

​
Describe Image

See an image you like but don’t know how to describe it? Describe Image uses AI vision to analyze an image and generate a detailed text prompt that captures its content, style, and composition.

​
How to Use

  1. Image detail dialog — open any image’s detail view and click the Describe Image button. The AI analyzes the image and generates a descriptive prompt.
  2. Drag and drop — drag any external image (or a gallery card) onto the Describe Image dropzone above the prompt editor in the generation sidebar.

​
What It Generates

The AI examines the image and produces a prompt describing:
  • Subject matter and scene composition
  • Art style and technique (photorealistic, illustration, watercolor, etc.)
  • Lighting, color palette, and mood
  • Camera angle and perspective
You can use the generated prompt as-is, or edit it to create variations of the original image.
Describe Image works well as a starting point. Combine it with Prompt Enhancement — first describe an image you like, then enhance the result for even more detail.

​
Video Generation

MeiGen offers several video models — the current list and full specs are on the Models page:
  • Seedance 2.5 — one quality level, per-second pricing, 4–30 seconds, up to 10 reference videos (30s in total, 200MB each) and up to 10 reference audio clips (30s in total)
  • Seedance 2.0 — three tiers, per-second pricing, 4–15 seconds, up to 3 reference videos (15s in total, 50MB each) and up to 3 reference audio clips (15s in total)
  • Veo 3.1 — two tiers, per-generation pricing, 4 / 6 / 8 seconds, audio always on
  • Grok Video 1.5 — Lite (default) / Standard, both at 480p / 720p / 1080p, 4–15 seconds; a first-frame image is required. Default Lite 480p × 4s costs 16 credits.
  • Agnes Video 2.5 Flash — per-second pricing, fixed 5 seconds, covered by daily free credits. Temporarily unavailable since 2026-09-22; it is not returned by List Models and requests to it are rejected until it is re-enabled.
Open the video sidebar from the Generate Video button in the floating dock on desktop, or from Generate in the bottom dock on mobile.

​
Storyboard — Video Prompt Builder

Click Storyboard in the video sidebar to turn a short idea into a production-ready prompt: a visual overview followed by a timed, shot-by-shot sequence. Set the output duration first; the generated timeline covers that duration without gaps and can include camera directions, dialogue, and sound cues.
Storyboard keeps your input language — write your idea in any language and the storyboard comes back in the same language. It requires sign-in and shares a daily AI-assist limit with the other prompt tools, but does not spend image/video generation credits.

​
Frame Images

Upload frame images to control the video’s composition:
  • First Frame — sets the starting composition of the video
  • Last Frame — sets the ending composition
Seedance 2.5, Seedance 2.0, and Veo 3.1 accept both frames (up to 2). Grok Video 1.5 and Agnes Video 2.5 Flash accept a first frame only. Frames are optional except on Grok Video 1.5, which is image-to-video only — a first frame is required, and the output ratio follows that image. You can also drag gallery cards directly as frame images.

​
HeyGen Video 1

HeyGen Video 1 is optimized from MiniMax H3 for affordable video with native audio. The model is available on Web, API and MCP, and capability-compatible App versions. Older Apps retain their existing catalog. Choose text-to-video, one first frame, or content references (up to 9 images and 3 audio clips). First-frame and content-reference panels are exclusive: only the selected panel is submitted. When the live catalog enables reference video, use up to 3 MP4 clips (1–5s and 16MB each, 15s total), alone or with content images. Do not combine video with separate reference audio; embedded audio is allowed. Video seconds are rounded up per clip and added to output seconds for billing. Existing HeyGen-compatible Apps can use reference video; incompatible video/audio combinations are rejected by the server before charging. Output is 5–15 seconds at 480p, 768p (default), 1080p or 2K. The price switches automatically between text/first-frame and content-reference rates. Audio adds no seconds but is part of the content-reference rate. Long prompts use the shared compression mechanism within the 32,000-character provider limit, preserving reference labels. See HeyGen limits and pricing for upload, ratio and credit details.

​
Seedance 2.5

Pricing: direct generation costs 18 / 39 / 90 credits per second at 480p / 720p / 1080p. With one or more reference videos, the rates are 11 / 24 / 54 credits per second, billed on the sum of the reference durations plus your output duration, with a minimum-billable floor. Reference audio adds nothing. The sidebar shows the exact total; see Models → Seedance 2.5 for the formula and examples. Seedance 2.5 has no Mini / Fast / Pro switch. Use Seedance 2.0 Pro when you specifically need 4K.

​
Seedance 2.0

Pricing: per-second; full formula (including the minimum-billable table for continuation) is in the Models page. The sidebar shows the exact total before you submit. Reference workflows:
  • Text-to-video: just write a prompt
  • Image-to-video: upload 1–2 frame images to control first/last frame
  • Content reference: attach up to 9 images to guide subject, style, or composition
  • Video extension: upload one or more reference videos (see the Extending a Video section below)
  • Reference audio: add WAV / MP3 clips to score or style the result — on Seedance 2.0 always alongside at least one image or video
Content-reference images, reference videos and reference audio can all be submitted in the same request: they are three independent budgets and never consume each other’s slots. Saved-character images share the content-image budget with user-uploaded images.
Adding reference videos makes the total credit cost depend on their length: billed seconds = “the sum of every reference video’s duration + your chosen duration” (never below the minimum-billable floor). More clips, or longer ones, cost more. Reference audio adds nothing — it is never billed, and a request carrying audio but no video is priced at the plain direct rate. The sidebar shows the exact total before you submit — confirm before clicking Generate.

​
Grok Video 1.5 — Lite / Standard

Select Lite (default) or Standard under the model picker. Both support 480p / 720p / 1080p and 4–15 second videos. Upload exactly one first-frame image; output follows its aspect ratio and includes generated audio. Reference videos and audio are not supported. Credits = tier-and-resolution rate × seconds: Lite costs 4 / 6 / 28 credits/sec at 480p / 720p / 1080p; Standard costs 16 / 28 / 50. Default Lite 480p × 4s costs 16 credits. Review the displayed total before submitting; see Models → Grok Video 1.5.

​
Veo 3.1 — Two Tiers, Native Audio

Pricing: per generation, depends on tier × duration. Full table is in Models → Veo 3.1.
Full specs and a side-by-side comparison of all video models are on the Models page.

​
Converting Images to Video

After generating an image, hover over the completed card and click the Animate button. This sends your generated image to the video sidebar as the first frame, making it easy to turn a still image into a short video clip.

​
Extending a Video

Seedance 2.5 and Seedance 2.0 support reference-video continuation. Upload one or more existing videos as visual conditioning input to guide the model toward generating a new segment that semantically continues the original.
Seedance 2.5: up to 10 reference videos, 2–30 seconds each and 30 seconds in total, up to 200MB per clip; 4–30 second output at 480p, 720p or 1080p.Seedance 2.0: up to 3 reference videos, 2–15 seconds each and 15 seconds in total, up to 50MB per clip; 4–15 second output. Mini / Fast offer 480p and 720p; Pro offers 720p and 1080p for continuation. 4K is direct-generation only.MeiGen detects each uploaded video’s actual duration automatically for billing and trimming. Reference audio can ride along in the same module and is never billed.

​
Three entry points

  1. From a video card: hover over any completed video card and click the Extend button in the top-left corner — the video is added to the Seedance sidebar as a reference
  2. Drag a video to the reference-image area: drag a video (local or from the gallery) onto the reference upload area — a confirmation popup asks “Use this as an extension reference?”
  3. Direct upload: in the Seedance sidebar’s Reference video & audio module, click + and pick local files — you can add several videos, and audio clips, in the same module

​
Workflow

  1. Trigger any of the entries above — the reference video appears in the module’s thumbnail grid. The two Extend entries (video-card button and drop-confirm popup) start a fresh continuation: they replace whatever is already in the module (videos and audio clips) and reset the prompt. + and drag-and-drop inside the module append to the current list instead
  2. The prompt box is auto-prefilled with "Extend this video with the following plot: " — keep this prefix and add your desired continuation
  3. Pick a supported resolution and output duration for the selected Seedance model
  4. Click Generate

​
Key behavior

Your prompt must explicitly say to extend the video. If the prompt only describes a scene without mentioning extension, the new segment may drift away from what you imagined as a “continuation” (the visuals will still be influenced by the reference, but the plot direction follows whatever your prompt says). The auto-prefilled Extend this video with the following plot: prefix exists to nudge the model toward “continuation” semantics — keep it and append your content.
Output length = your selected duration (4–30 seconds on Seedance 2.5; 4–15 on Seedance 2.0), independent of the reference videos’ lengths. The reference videos act as visual conditioning input and are not concatenated into the output. To create a continuous “original + new” video, stitch the clips in a video editor.

​
Pricing

Both models use max(sum of reference video durations + output duration, minimum-billable floor). Reference audio is free and never enters that sum.
  • Seedance 2.5: 480p 11 credits/sec; 720p 24 credits/sec; 1080p 54 credits/sec. A single 2-second reference + 5-second output bills 9 seconds, for 99 / 216 / 486 credits. Add a second, 3-second reference and the sum becomes 5 seconds, so the same 5-second output bills max(5 + 5, 9) = 10 seconds — 110 / 240 / 540 credits. Attaching audio on top of either leaves the total unchanged.
  • Seedance 2.0: the rate depends on Mini / Fast / Pro and resolution, with the same sum-of-references rule. See Models → Seedance 2.0 for the full matrix.

​
Generation History

After submitting a generation request, your images appear as cards in the generation history panel (accessible via the floating dock’s History button or the sidebar).

​
Pending State

Cards show live progress while generating; video generations also display an estimated completion time (e.g., 2–5 min). Typical generation times by model:

​
Failed State

If a generation fails, the card shows:
  • The reason for failure
  • “Credits refunded” note — credits are automatically returned when a generation fails
  • Retry button — click to resubmit the same request with the original prompt and settings

​
Completed State

Hover over a completed generation card to reveal action buttons: The card also shows the aspect ratio and resolution labels in the bottom-left corner.

​
Credits and Billing

MeiGen uses a dual credit system:
  • Daily credits: a free daily allowance that resets at 00:00 UTC, usable on basic models — currently Flux 3 Image Klein and Agnes Image 2.5 Flash, both image models. Agnes Video 2.5 Flash, the only video model daily credits covered, has been temporarily unavailable since 2026-09-22, so there is no basic-tier video model right now. They are grouped under Basic Models in the model picker.
  • Purchased credits: your non-expiring balance, shown as Credits in the sidebar. It covers everything outside the daily allowance — credits you topped up, plus any bonus credits granted to your account (sign-up welcome bonus, referral rewards). Usable on all models.
Generating with premium models (GPT Image 2.5, GPT Image 2.0, Nanobanana 2 / 2.1 / Pro, Seedream, Midjourney V8.2, Grok Imagine Image 2.0, Seedance 2.5 / 2.0, Veo 3.1, Grok Video 1.5, and so on) requires welcome or purchased credits — daily credits never apply to them, whether or not you have purchased before. API Token calls only use purchased credits, regardless of the model; daily credits never apply to the API path. The credit cost is shown on the Generate button before you submit. Hover over the credits card at the bottom of the left sidebar to see your balance breakdown.

​
Free vs Paid

The “Images per request” limit applies to the Web UI only. Each API call always returns 1 image (Midjourney V8.2 always returns 4 candidates per call). Creating an API token does not require a paid account — any account can issue one from Settings → API Keys. What API calls do require is purchased credits, since daily free credits never apply on the API path.

​
FAQ

Generation times vary by model and server load. See the table at the top of this section for typical times.
Credits are automatically refunded when a generation fails. The refund is reflected immediately in your balance. You can use the Retry button to try again.
Use the Retry button on a failed card, or click Use Idea on a completed card to copy its prompt back to the editor. Note that AI generation is non-deterministic — even with the same prompt, results will vary.
Cutout removes the background from a still image, creating a transparent PNG. Animate converts the still image into a short video clip using the video generation model. GPT Image 2 and 2.5 also accept explicit requests for transparent backgrounds in the prompt; the alpha channel depends on intent detection and the output. Cutout removes the background from an existing image.
The top resolution of each model is reserved for paid users — 4K on models offering 2K / 4K, and 2K on models offering 1K / 2K. Upgrade your account to unlock it.