Skip to main content
MeiGen supports multiple AI models for image and video generation. Use the comparison table below to pick one, then scroll to its section for detailed specs.

​
Quick Comparison

ModelCreditsSpeedRef ImagesBest For
GPT Image 2.0 (default)2–80 (by resolution × quality)Medium (~45s)5Best accuracy & aesthetics, text rendering
Nanobanana Pro10Fast (~45s)5High quality, complex scenes
Nanobanana 25Fast (~38s)5General use, wide ratio support
Seedream 5.0 Lite5Fast (~35s)5Photorealism, 3K output
Seedream 4.55Fast (~17s)5Product photos, marketing
Midjourney V8.115 (1K) / 20 (2K)Slow (~45s)1Photorealistic, universal aesthetics
Flux 2 Klein2Fast (~18s)NoneGeneral-purpose base model, text rendering
Z Image Turbo2Fastest (~12s)NoneQuick drafts, prototyping
Seedance 2.0Per-second (Fast 13–22/sec, Pro 13–42/sec)Video, ~1-4minFirst/last frame + reference videoTwo tiers (Fast / Pro), 4–15s, multiple ratios, audio
Happyhorse 1.0Per-second (720p 18/sec, 1080p 28/sec)Video, ~1-2minFirst frame (single image)3–15s adjustable duration, text-to-video + first-frame i2v, audio included
Veo 3.1Per generation (Fast 80–165, Pro 220–435)Video, ~1-7minUp to 2 (first/last frame)Two tiers (Fast / Pro), 4/6/8s, 720p/1080p/4k same price, audio
GPT image 1.5 was retired on 2026-04-22 (replaced by GPT Image 2.0). Midjourney V7 was replaced by V8.1 on 2026-05-09.

​
Image Models

​
GPT Image 2.0

Model IDgpt-image-2
ProviderOpenAI
CreditsBy resolution × quality — see table below
Reference imagesUp to 5
Resolutions1K, 2K, 4K
QualityStandard / Medium / High
Aspect ratios1:1, 3:2, 2:3, 16:9, 9:16, 4:3, 3:4, 5:4, 4:5, 21:9, 9:21
Credit matrix:
StandardMediumHigh
1K21018
2K52040
4K103280
All resolutions consume welcome or purchased credits (premium model — daily free credits don’t apply). 4K is paid-only. The current default model and MeiGen’s best overall image model. Excels at instruction following, in-image text rendering, and complex multi-element scenes.
Stricter moderation: prompts involving real people, celebrities, brand logos, or violent/adult content may be rejected. Rephrase to drop specific names or try a different model.

​
Nanobanana 2

Model IDnanobanana-2
ProviderGoogle (Gemini)
Credits5 per image
Reference imagesUp to 5
Resolutions2K, 4K
Aspect ratios1:1, 3:4, 4:5, 2:3, 9:16, 1:4, 1:8, 4:3, 5:4, 3:2, 16:9, 21:9, 4:1, 8:1
The most affordable Gemini model with the widest range of aspect ratios, including ultra-wide (8:1) and ultra-tall (1:8) options. Good for quick iterations and exploration.
Content moderation: Nanobanana 2 has stricter content filtering than other models. Prompts that mention celebrities, brand names, real people, or face-swap scenarios are more likely to be rejected. If your prompt is flagged, try rephrasing to avoid specific names or use a different model.

​
Nanobanana Pro

Model IDgemini-3-pro-image-preview
ProviderGoogle (Gemini)
Credits10 per image
Reference imagesUp to 5
Resolutions2K, 4K
Aspect ratios1:1, 3:4, 4:5, 2:3, 9:16, 4:3, 5:4, 3:2, 16:9, 21:9
The premium Gemini model with higher image quality. Better at complex scenes, fine details, and text rendering. Choose this when quality matters more than cost.

​
Seedream 5.0 Lite

Model IDseedream-5.0-lite
ProviderByteDance
Credits5 per image
Reference imagesUp to 5
Resolutions2K, 3K
Aspect ratios1:1, 3:4, 4:3, 16:9, 9:16, 3:2, 2:3, 21:9
ByteDance’s latest lightweight model. Offers good quality at low cost with optional 3K resolution output. Strong at photorealistic content and Chinese-style aesthetics.

​
Seedream 4.5

Model IDseedream-4.5
ProviderByteDance
Credits5 per image
Reference imagesUp to 5
Resolutions2K, 4K
Aspect ratios1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9
The previous generation Seedream model. Still produces solid results, particularly good for product photography and marketing visuals.

​
Midjourney V8.1

Model IDmidjourney-v8.1
ProviderMidjourney
Credits15 (1K) / 20 (2K) per generation
Reference images1 (content or style reference)
Resolutions1K (1024×1024) / 2K (2048×2048) — default 1K
Aspect ratios1:1, 4:3, 3:2, 16:9, 3:4, 2:3, 9:16
QualityStandard / High — default High (same price)
Midjourney’s photorealistic flagship. Returns 4 candidate images per generation (charged once). Choose 2K for native high-resolution output, High quality for finer detail at no extra cost. Features:
  • Content and style reference modes
  • Advanced parameters (stylize, chaos, raw, etc.) for fine-tuning the output
  • Auto-translates non-English prompts to English
  • Native 2K output toggle
  • Quality (Standard / High) toggle

​
Flux 2 Klein

Model IDflux2-klein
ProviderBlack Forest Labs
Credits2 per image
Daily free creditsEligible
Reference imagesNot supported
Aspect ratiosAuto, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3
A base model from Black Forest Labs, suited to everyday general-purpose creation.

​
Z Image Turbo

Model IDz-image-turbo
ProviderAlibaba (Qwen)
Credits2 per image
Daily free creditsEligible
Reference imagesNot supported
ResolutionsFixed
Aspect ratios1:1, 2:3, 3:2, 3:4, 4:3, 7:9, 9:7, 9:16, 9:21, 16:9, 21:9
The fastest and cheapest model — ideal for quick drafts when you need results in seconds.
No reference image support. Z Image Turbo generates images from text only — you cannot upload reference images with this model. If you need to use reference images, choose a different model.

​
Video Models

​
Seedance 2.0

Model IDseedance-2-0
ProviderByteDance
CreditsPer-second pricing (see below)
Duration4-15 seconds (default 5)
Reference imagesFirst/last frame (image-to-video)
Reference videoYes (separate With-reference-video rate table, Pro has no 480p tier)
Resolutions480p, 720p, 1080p
Aspect ratiosadaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9
AudioAuto-generated
ByteDance’s latest video generation model. Supports text-to-video, image-to-video (first/last frame), and video continuation. All outputs include AI-generated audio. The adaptive aspect ratio automatically matches the reference image/video dimensions. Two tiers — pick one via the Speed / Quality segmented control inside the video sidebar. Same Seedance 2.0 model, same params, just different rendering quality and price:
  • Fast (default) — quick turnaround, 1080p is upscaled from 720p
  • Pro — higher fidelity, native 1080p rendering

​
Pricing

Per-second. Rate depends on tier (Fast / Pro) × whether a reference video is uploaded:
ResolutionFast DirectFast With reference videoPro DirectPro With reference video
480p13/sec8/sec14/sec—
720p20/sec14/sec22/sec16/sec
1080p22/sec14/sec42/sec28/sec
Pro doesn’t offer a 480p With-reference-video rate (use 720p+ on Pro, or fall back to Fast). With-reference-video billing rule (both tiers): billable seconds = max(reference video duration + your selected duration, min billable) Output length is always your selected duration (4–15), independent of the reference video’s length.
Your selected duration (sec)456789101112131415
Min billable (sec)7910121415171920222425

​
Examples

ScenarioCalculationTotal
Fast 480p × 5s direct13 × 565
Fast 720p × 5s direct20 × 5100
Fast 1080p × 10s direct22 × 10220
Fast 720p, 5s reference + 10s selected duration14 × max(5+10, 17) = 14 × 17238
Pro 720p × 5s direct22 × 5110
Pro 1080p × 5s direct42 × 5210
Pro 1080p, 5s reference + 10s selected duration28 × max(5+10, 17) = 28 × 17476
If generation fails, the full credit amount is automatically refunded — including all per-second charges.

​
Happyhorse 1.0

Model IDhappyhorse-1.0
ProviderAlibaba
CreditsPer-second (see below)
Duration3–15 seconds (default 5)
Reference images1 (first frame, image-to-video)
Reference videoNot supported
Resolutions720p, 1080p (default 720p)
Aspect ratiosAuto, 16:9, 9:16, 1:1, 4:3, 3:4
AudioAuto-generated
Alibaba’s video model — text-to-video and single-image first-frame image-to-video. AI-generated audio included. No reference-video continuation. Auto aspect ratio infers the output ratio from your prompt or reference image.

​
Pricing

ResolutionRate
720p18 credits/sec
1080p28 credits/sec
Examples:
ScenarioCalculationTotal
720p × 5s18 × 590
720p × 10s18 × 10180
1080p × 5s28 × 5140
1080p × 10s28 × 10280
If generation fails, the full credit amount is automatically refunded.

​
Veo 3.1

Model IDveo-3.1
ProviderGoogle
CreditsPer generation (see below)
Duration4, 6, or 8 seconds (default 4)
Reference imagesUp to 2 (as first/last frame)
Reference videoNot supported
Resolutions720p, 1080p, 4k (default 1080p)
Aspect ratiosAuto, 16:9, 9:16
AudioAuto-generated (always on)
Google’s video generation model. Creates short clips with AI-generated audio synced to the prompt. Auto aspect ratio infers the output ratio from your prompt or reference image. Pick this for premium visual quality with native audio; for longer durations (>8s) or wider ratio support, use Seedance 2.0. Two tiers — pick one via the Speed / Quality segmented control inside the video sidebar. Same Veo 3.1 model, same params, just different rendering quality and price:
  • Fast (default) — quick turnaround, balanced quality
  • Pro — higher fidelity, longer rendering time

​
Pricing

Per generation. Price depends on tier (Fast / Pro) × duration (4 / 6 / 8s). All resolutions (720p / 1080p / 4k) share the same price — pick the resolution you want at no extra cost (4k takes noticeably longer to render).
DurationFastPro
4s80220
6s125330
8s165435

​
Examples

ScenarioTotal
Fast 4s (any resolution)80
Fast 8s (any resolution)165
Pro 4s (any resolution)220
Pro 8s 4k435
If generation fails, the full credit amount is automatically refunded.

​
Known Limitations

This model is more sensitive to content involving real people, celebrities, brand logos, and face-swap requests. Prompts that work on other models may be rejected here. If you get a content violation error, rephrase your prompt to remove specific names or try a different model.
Both base models generate images from text only. The reference image upload section will be hidden when either is selected. If you need to use reference images, switch to any other model.
Unlike other models that support up to 5 reference images, Midjourney V8.1 only accepts 1 reference image. However, it offers more control over how the reference is used (content vs. style reference).
Unlike other models that return a single image, Midjourney V8.1 returns 4 candidate images per generation. All candidates are saved and can be browsed in the image detail dialog. You are only charged once (15 credits at 1K / 20 credits at 2K) for all 4 images.
Unlike Seedance 2.0, Happyhorse does not support video continuation. Reference image input is single first-frame only. For continuation, use Seedance 2.0.
GPT Image 2.0 applies stricter moderation than other models to real people, celebrities, brand logos, and adult/violent content. Rephrase your prompt to drop specific names, or try a different model.
Seedance bills per second, not per image — and uploading a reference video uses a separate rate table with a minimum-billable floor. See the Seedance 2.0 section above for the full rates and formula.
Veo 3.1 only supports 16:9 / 9:16 (plus Auto). Square (1:1), 4:3 / 3:4 portrait, and other ratios are not available. For wider ratio support, use Seedance 2.0 or Happyhorse 1.0.
720p / 1080p / 4k all cost the same on Veo 3.1, so you can pick 4k for free. The trade-off is rendering time — 4k typically takes 6–8 minutes versus 1–4 minutes for 720p / 1080p.