# Uptown Funk AI

> Create your Uptown Funk MV with your own cast and the original soundtrack. Explore motion transfer, object swap, restyling, and image/video tools.

Canonical website: https://uptownfunkai.com/
Generated from the deployed site configuration. Prices are in USD.

## Main offer: Pay per MV

- Output: 15 seconds, 480p, 16:9 MP4 with the original soundtrack.
- Input: 1–9 cast photos, one person per photo; start with the lead, then add supporting people.
- Photos: JPG, PNG or WebP; up to 8 MB each, 300–6000 pixels per side, aspect ratio 0.4–2.5.
- One-time purchase: $9.90 adds 255 universal credits. No subscription or automatic renewal.
- One MV reserves up to 255 credits. Final settlement can be lower; any difference returns automatically. Failed generations return reserved credits.
- Buying credits does not start a generation. Choose photos and explicitly create the MV.
- Universal credits also work in the image and video tools. Leftover credits remain in the wallet.
- Cost accounting: 1 site credit is US $0.01 of generation cost; this is not a promise that credit packs sell at $0.01 per credit. Our observed 15-second-source MV task cost 493 provider credits ($2.465), rounded to 247 site credits. Reserve 255; actual provider charges may vary.
- Monthly plans, annual plans and one-time credit packs are also available.
- Browsing examples and reading documentation do not consume credits. Paid generation requires sign-in and sufficient credits; no free signup credit grant is promised here.
- Other workflows: editable Opus motion graphics and Seedream layer decomposition use operation-specific quotes; browser image utilities use no generation credits.

## Start here

- [MV studio](https://uptownfunkai.com/#home-studio-section)
- [Pricing](https://uptownfunkai.com/pricing)
- [Motion Transfer](https://uptownfunkai.com/motion-transfer)
- [Object Swap](https://uptownfunkai.com/object-swap)
- [Restyle](https://uptownfunkai.com/restyle)
- [Preset library](https://uptownfunkai.com/presets)
- [Image tools](https://uptownfunkai.com/ai-image-generator)
- [Video tools](https://uptownfunkai.com/ai-video-generator)

## Guides for the general remix workspace

- [Choose Motion Transfer or Object Swap](https://uptownfunkai.com/blog/genjutsu-motion-transfer-vs-object-swap)
- [Prepare character, outfit and product references](https://uptownfunkai.com/blog/genjutsu-reference-images)
- [Map multiple characters](https://uptownfunkai.com/blog/genjutsu-multiple-characters)
- [Check source video and credit quotes](https://uptownfunkai.com/blog/genjutsu-source-video-and-credits)

## Policies and contact

Uptown Funk AI is an independent video studio. The CEO remix is credited to its original X creator and was not generated on this site. The wizard and football examples were generated with this workflow. The three synchronized previews are 12.4 seconds; the MV creation template is approximately 15 seconds. The wizard preview has two similar supporting faces, and generated anatomy, identities and lip movements may vary.
- [Privacy Policy](https://uptownfunkai.com/privacy-policy)
- [Terms of Service](https://uptownfunkai.com/terms-of-service)
- [Refund Policy](https://uptownfunkai.com/refund-policy)
- Contact: hi@uptownfunkai.com

## AI documents

- [Pricing and credits](https://uptownfunkai.com/pricing.md)
- [Models and tool capabilities](https://uptownfunkai.com/models.md)
- [Combined reference](https://uptownfunkai.com/llms-full.txt)

---

# Uptown Funk AI pricing and credits

Canonical page: https://uptownfunkai.com/pricing
Generated from the deployed purchase and quote configuration. All prices are USD.

## Pay per MV — recommended

- One-time purchase: $9.90 adds 255 universal credits. No subscription or automatic renewal.
- One MV reserves up to 255 credits. Final settlement can be lower; any difference returns automatically. Failed generations return reserved credits.
- Buying credits does not start a generation. Choose photos and explicitly create the MV.
- Universal credits also work in the image and video tools. Leftover credits remain in the wallet.
- Cost accounting: 1 site credit is US $0.01 of generation cost; this is not a promise that credit packs sell at $0.01 per credit. Our observed 15-second-source MV task cost 493 provider credits ($2.465), rounded to 247 site credits. Reserve 255; actual provider charges may vary.
- One-time MV purchase credits do not expire. Quantities 1–100 multiply the purchase price and credit grant.

## Monthly subscriptions

| Plan | Price per month | Credits per month | MV equivalent |
| --- | --- | --- | --- |
| Lite | $29.90 | 600 | 2 MVs + 90 credits at the maximum reservation; observed estimate ~2 MVs at 247 each |
| Standard | $49.90 | 1,500 | 5 MVs + 225 credits at the maximum reservation; observed estimate ~6 MVs at 247 each |
| Pro | $99.90 | 3,600 | 14 MVs + 30 credits at the maximum reservation; observed estimate ~14 MVs at 247 each |
| Max | $199.90 | 8,000 | 31 MVs + 95 credits at the maximum reservation; observed estimate ~32 MVs at 247 each |

Monthly grants are valid for 30 days. Cancel anytime.

## Annual subscriptions

| Plan | Total billed per year | Annual total (1/12 monthly) | MV equivalent |
| --- | --- | --- | --- |
| Lite | $179.00 | 7,200 | 28 MVs + 60 credits at the maximum reservation; observed estimate ~29 MVs at 247 each |
| Standard | $299.00 | 18,000 | 70 MVs + 150 credits at the maximum reservation; observed estimate ~72 MVs at 247 each |
| Pro | $599.00 | 43,200 | 169 MVs + 105 credits at the maximum reservation; observed estimate ~174 MVs at 247 each |
| Max | $1199.00 | 96,000 | 376 MVs + 120 credits at the maximum reservation; observed estimate ~388 MVs at 247 each |

New annual purchases deliver 1/12 of the annual total each month for 12 months, beginning after payment. Unused credits accumulate; all allocations expire at the paid annual period end. Legacy upfront orders retain their original terms. Existing subscriptions switch only at a renewal at least 30 days after acknowledgment of the billing notice. Annual prices above are total charges, not monthly charges.
Max supports 1x–5x: multiply the complete price and credit grant before calculating the MV equivalent.

## One-time credit packs

| Pack | Price | Credits | MV equivalent |
| --- | --- | --- | --- |
| Starter | $39.90 | 800 | 3 MVs + 35 credits at the maximum reservation; observed estimate ~3 MVs at 247 each |
| Value | $79.90 | 2,000 | 7 MVs + 215 credits at the maximum reservation; observed estimate ~8 MVs at 247 each |
| Pro | $199.90 | 7,500 | 29 MVs + 105 credits at the maximum reservation; observed estimate ~30 MVs at 247 each |
| Bulk | $999.90 | 50,000 | 196 MVs + 20 credits at the maximum reservation; observed estimate ~202 MVs at 247 each |
| Mega | $2599.00 | 160,000 | 627 MVs + 115 credits at the maximum reservation; observed estimate ~647 MVs at 247 each |

Credit pack grants are valid for 365 days. No subscription. Premium subscription perks require an active subscription.

## Credit and refund rules

MV equivalents use 255 credits per MV as the maximum reservation; they are examples of spending the same credit grant, not extra MV passes.
Image/video charges depend on the selected model, inputs and output settings. Review the workspace quote before submitting.
Catalog prices exclude checkout taxes and any eligible checkout promotion. Final checkout total governs the purchase.
Failed generation credit returns are separate from cash refunds. Earlier MV purchases retain their original cash refund terms. Cash refund eligibility follows the Refund Policy.
- [Refund Policy](https://uptownfunkai.com/refund-policy)
- [Model quotes and options](https://uptownfunkai.com/models.md)

## Configured model quote examples

These are default-setting examples from the workspace quote engine, not guaranteed fixed output counts. Resolution, duration, reference inputs, quality and output count can change the final quote.
- Genjutsu Motion Transfer: From 128 credits · default 4s input · 480p.
- Genjutsu Object Swap: From 128 credits · default 4s input · 480p.
- Genjutsu Restyle: Conservative budget 255 credits · default 4s input · 480p · no character images; +100 credits/image.
- MiniMax H3 Max Turbo: From 7 credits · default 5s · 480P.
- MiniMax H3: From 130 credits · default 5s · 2K.
- H3 Max: From 50 credits · default 5s · 768P.
- Seedance 2.5: From 84 credits · default 4s · 480p.
- Seedance 2.0 Fast: From 44 credits · default 4s · 480p.
- Seedance 2.0 Pro: From 55 credits · default 4s · 480p.
- Seedance 2.0 Mini: From 29 credits · default 4s · 480p.
- Seedance 1.5 Pro: From 5 credits · default 4s · 480p.
- Wan 2.7: From 50 credits · default 5s · 720p.
- Wan 2.6: From 50 credits · default 5s · 720p.
- Grok Imagine: From 42 credits · default 6s · 720p.
- Kling 3.0: From 26 credits · default 3s · 720p.
- PixVerse Extend: From 20 credits · default 5s · 720p.
- ByteDance Video Upscaler: From 4 credits · default 5s input · 1080p.
- Bria Video Background Removal: From 70 credits · default 5s input · source.
- PixVerse Person Swap: From 20 credits · default 5s input · 720p.
- Sync Lip Sync 2: From 25 credits · default 5s input · source.
- Sync Talking Photo: From 67 credits · default 5s input · source.
- Hailuo 02 Pro: From 48 credits · default 6s · 1080p.
- Hailuo 02 Standard: From 27 credits · default 6s · 768p.
- Hailuo 2.3 Pro: From 49 credits · default 6s · 1080p.
- Hailuo 2.3 Standard: From 28 credits · default 6s · 768p.
- Seedance 1.0 Pro: From 61 credits · default 5s · 1080p.
- Wan 2.5: From 75 credits · default 5s · 1080p.
- Kling 2.6 Pro: From 70 credits · default 5s · 1080p.
- Veo 3.1: From 320 credits · default 8s · 720p.
- HappyHorse 1.0: From 140 credits · default 5s · 1080p.
- HappyHorse 1.1: From 90 credits · default 5s · 1080p.
- Grok Imagine 1.5: From 84 credits · default 6s · 720p.
- H3 Max Styles: From 40 credits · default 5s · 768P.
- H3 Max Camera Control: From 40 credits · default 5s · 768P.
- H3 Max Lip Sync: From 40 credits · default 5s input · 768P.
- Gemini Omni: From 100 credits · default 8s · 720p.
- H3 LoRA: From 38 credits · default 5s · 768P.
- Seedream 5.0 Pro: Generate: 1K 7 · 2K 14 credits/image; extra edit references quoted in the workspace. Layer reserve: Auto/1K/1.5K 72 · 2K 144 credits; settles by actual layers with excess refunded.
- GPT Image 2.5 Flare: 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling..
- GPT Image 2.5 Sunburst: 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling..
- GPT Image 2: Square/auto: 1K 19 · 2K 25 · 4K 38; non-square: 1K 22 · 2K 27 · 4K 41 credits/image.
- Nano Banana 2: 1K 8 · 2K 12 · 4K 16 credits/image.
- Nano Banana Pro: 1K 15 · 2K 15 · 4K 30 credits/image.
- Nano Banana: default 4 credits/image.
- Seedream 5 Lite: 2K 4 · 3K 4 credits/image.
- Seedream 4.5: 2K 4 · 4K 4 credits/image.
- Seedream V4: 1K 4 · 2K 4 · 4K 4 credits/image.
- Bria RMBG 2.0: original 4 credits/image.
- Illusion Diffusion: 1K 4 credits/image.
- Z-Image: default 4 credits/image.
- Nano Banana 2 Lite: 1K 5 credits/image.
- GPT Image 1.5: 1K 14 credits/image.

## Separate workflow charges

- Opus 5.5 · Motion Graphics: per create/revision operation, not per second. A default 20s, 16:9, sketch title with no image elements reserves 71 credits; the input/output budget caps a reservation at 92. The confirmed quote depends on the brief, approved elements and existing scene. Final receipt settlement is capped at the reservation; excess credits return. Invalid/failed generations return the reservation. Preview/export of an existing scene does not call the generation model.
- Seedream 5.0 Pro layer decomposition, auto: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 1K: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 1.5K: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 2K: reserve 144 credits for up to 16 billable layers; one-layer quote 9 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Browser image utilities consume 0 generation credits. Processing/history requires sign-in and verified email; inputs and outputs are saved to the account. This is separate from paid AI image models.

---

# Uptown Funk AI models and tools

Canonical website: https://uptownfunkai.com/
Generated from the deployed workspace model catalog and shared quote display engine. These are website capabilities; availability follows the current workspace.

## Uptown Funk MV — main offer

- Model: Seedance 2.5 (bytedance/seedance-2-5).
- Input: 1–9 photos, one person per photo. The homepage uses its preset source performance.
- Output: 15 seconds, 480p, 16:9, MP4 with the original soundtrack.
- Quote: reserve up to 255 credits; a lower final charge returns the difference.
- [Open MV studio](https://uptownfunkai.com/#home-studio-section)

## Opus 5.5 · Motion Graphics (claude-opus-5-5-motion) — separate motion workflow

- Creates an editable scene of shapes, text and approved image elements, not photorealistic footage. No generated audio. Revisions preserve the original duration, ratio and style.
- Inputs: a motion brief, up to 4 approved raster images, optionally a confirmed public website brief or an owned base version.
- Duration: 10, 15, 20, 30 seconds; ratios: 16:9, 9:16, 1:1; styles: sketch, motion.
- Defaults: 20s, 16:9, 720p, audio off; MP4 export resolutions: 720p, 1080p.
- Opus 5.5 · Motion Graphics: per create/revision operation, not per second. A default 20s, 16:9, sketch title with no image elements reserves 71 credits; the input/output budget caps a reservation at 92. The confirmed quote depends on the brief, approved elements and existing scene. Final receipt settlement is capped at the reservation; excess credits return. Invalid/failed generations return the reservation. Preview/export of an existing scene does not call the generation model.
- [Open motion workspace](https://uptownfunkai.com/opus-5-5-video-generator)

## General video workspace

- [Open video workspace](https://uptownfunkai.com/ai-video-generator)
Quotes below identify default settings. Input video/audio duration, references, resolution and other options can change the quote; inspect the final quote before submitting.

### Genjutsu Motion Transfer (genjutsu-motion-transfer)

- Modes: reference; operation: motion-transfer.
- Input limits: 8 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 8 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 10000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 4–30 (step 1) seconds.
- Default audio: off.
- Defaults: reference, 4s, 480p, adaptive. Audio: no optional audio generation.
- Credits: From 128 credits · default 4s input · 480p.

### Genjutsu Object Swap (genjutsu-object-swap)

- Modes: reference; operation: object-swap.
- Input limits: 8 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 8 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 10000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 4–30 (step 1) seconds.
- Default audio: off.
- Defaults: reference, 4s, 480p, adaptive. Audio: no optional audio generation.
- Credits: From 128 credits · default 4s input · 480p.

### Genjutsu Restyle (genjutsu-restyle)

- Modes: reference; operation: restyle.
- Input limits: 5 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 5 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 10000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 4–30 (step 1) seconds.
- Default audio: off.
- Defaults: reference, 4s, 480p, adaptive. Audio: no optional audio generation.
- Credits: Conservative budget 255 credits · default 4s input · 480p · no character images; +100 credits/image.

### MiniMax H3 Max Turbo (minimax-h3-max-turbo)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 50000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480P, 768P, 1080P.
- Duration: 5–15 (step 1) seconds.
- Default audio: on.
- Defaults: text, 5s, 480P, 16:9. Audio: native.
- Credits: From 7 credits · default 5s · 480P.

### MiniMax H3 (minimax-h3)

- Modes: reference, text, image.
- Input limits: 9 images, 3 videos, 3 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 9 images, 3 videos, 3 audio files (12 total); ratios: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 7000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 2K.
- Duration: 5–15 (step 1) seconds.
- Default audio: off.
- Defaults: reference, 5s, 2K, adaptive. Audio: no optional audio generation.
- Credits: From 130 credits · default 5s · 2K.

### H3 Max (minimax-h3-max)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480P, 768P.
- Duration: 5–15 (step 1) seconds.
- Default audio: on.
- Defaults: text, 5s, 768P, 16:9. Audio: native.
- Credits: From 50 credits · default 5s · 768P.

### Seedance 2.5 (seedance-2.5)

- Modes: reference, text, image.
- Input limits: 30 images, 10 videos, 10 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 30 images, 10 videos, 10 audio files (50 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p.
- Duration: 4–30 (step 1) seconds.
- Default audio: on.
- Defaults: reference, 4s, 480p, adaptive. Audio: optional.
- Credits: From 84 credits · default 4s · 480p.

### Seedance 2.0 Fast (seedance-2.0-fast)

- Modes: reference, text, image.
- Input limits: 9 images, 3 videos, 3 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 9 images, 3 videos, 3 audio files (12 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p.
- Duration: 4–15 (step 1) seconds.
- Default audio: on.
- Defaults: reference, 4s, 480p, adaptive. Audio: optional.
- Credits: From 44 credits · default 4s · 480p.

### Seedance 2.0 Pro (seedance-2.0-pro)

- Modes: reference, text, image.
- Input limits: 9 images, 3 videos, 3 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 9 images, 3 videos, 3 audio files (12 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p, 4k.
- Duration: 4–15 (step 1) seconds.
- Default audio: on.
- Defaults: reference, 4s, 480p, adaptive. Audio: optional.
- Credits: From 55 credits · default 4s · 480p.

### Seedance 2.0 Mini (seedance-2.0-mini)

- Modes: reference, text, image.
- Input limits: 9 images, 3 videos, 3 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 9 images, 3 videos, 3 audio files (12 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p.
- Duration: 4–15 (step 1) seconds.
- Default audio: on.
- Defaults: reference, 4s, 480p, adaptive. Audio: optional.
- Credits: From 29 credits · default 4s · 480p.

### Seedance 1.5 Pro (seedance-1.5-pro)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 4, 8, 12 seconds.
- Default audio: off.
- Defaults: text, 4s, 480p, 16:9. Audio: optional.
- Credits: From 5 credits · default 4s · 480p.

### Wan 2.7 (wan-2.7)

- Modes: text, image.
- Input limits: 2 images, 1 videos, 1 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1, 4:3, 3:4.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 5000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p, 1080p.
- Duration: 2–15 (step 1) seconds.
- Default audio: off.
- Defaults: text, 5s, 720p, 16:9. Audio: no optional audio generation.
- Credits: From 50 credits · default 5s · 720p.

### Wan 2.6 (wan-2.6)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: inferred from input.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 1500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p, 1080p.
- Duration: 5, 10, 15 seconds.
- Default audio: off.
- Defaults: text, 5s, 720p, 16:9. Audio: no optional audio generation.
- Credits: From 50 credits · default 5s · 720p.

### Grok Imagine (grok-imagine)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1, 3:2, 2:3.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 5000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p.
- Duration: 6, 10 seconds.
- Default audio: off.
- Defaults: text, 6s, 720p, 16:9. Audio: no optional audio generation.
- Styles: normal, fun, spicy.
- Credits: From 42 credits · default 6s · 720p.

### Kling 3.0 (kling-3.0)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 2500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p.
- Duration: 3–15 (step 1) seconds.
- Default audio: off.
- Defaults: text, 3s, 720p, 16:9. Audio: optional.
- Versions: standard, pro.
- Credits: From 26 credits · default 3s · 720p.

### PixVerse Extend (pixverse-extend)

- Modes: reference; operation: extend.
- Input limits: 0 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 0 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 360p, 540p, 720p, 1080p.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, 720p, adaptive. Audio: no optional audio generation.
- Credits: From 20 credits · default 5s · 720p.

### ByteDance Video Upscaler (bytedance-video-upscaler)

- Modes: reference; operation: upscale.
- Input limits: 0 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 0 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 1080p, 2k, 4k.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, 1080p, adaptive. Audio: no optional audio generation.
- Credits: From 4 credits · default 5s input · 1080p.

### Bria Video Background Removal (bria-video-background)

- Modes: reference; operation: remove-background.
- Input limits: 0 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 0 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: source.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, source, adaptive. Audio: no optional audio generation.
- Credits: From 70 credits · default 5s input · source.

### PixVerse Person Swap (pixverse-swap)

- Modes: reference; operation: swap.
- Input limits: 1 images, 1 videos, 0 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 1 images, 1 videos, 0 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 360p, 540p, 720p.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, 720p, adaptive. Audio: no optional audio generation.
- Credits: From 20 credits · default 5s input · 720p.

### Sync Lip Sync 2 (sync-lipsync-2)

- Modes: reference; operation: lipsync.
- Input limits: 0 images, 1 videos, 1 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 0 images, 1 videos, 1 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: source.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, source, adaptive. Audio: no optional audio generation.
- Credits: From 25 credits · default 5s input · source.

### Sync Talking Photo (sync-talking-photo)

- Modes: reference; operation: talking-photo.
- Input limits: 1 images, 0 videos, 1 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 1 images, 0 videos, 1 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: source.
- Duration: 5 seconds.
- Default audio: off.
- Defaults: reference, 5s, source, adaptive. Audio: no optional audio generation.
- Credits: From 67 credits · default 5s input · source.

### Hailuo 02 Pro (hailuo-02-pro)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: inferred from input.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 1080p.
- Duration: 6 seconds.
- Default audio: off.
- Defaults: text, 6s, 1080p, 16:9. Audio: no optional audio generation.
- Credits: From 48 credits · default 6s · 1080p.

### Hailuo 02 Standard (hailuo-02-standard)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: inferred from input.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 768p.
- Duration: 6, 10 seconds.
- Default audio: off.
- Defaults: text, 6s, 768p, 16:9. Audio: no optional audio generation.
- Credits: From 27 credits · default 6s · 768p.

### Hailuo 2.3 Pro (hailuo-2.3-pro)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: inferred from input.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 1080p.
- Duration: 6 seconds.
- Default audio: off.
- Defaults: text, 6s, 1080p, 16:9. Audio: no optional audio generation.
- Credits: From 49 credits · default 6s · 1080p.

### Hailuo 2.3 Standard (hailuo-2.3-standard)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: inferred from input.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 768p.
- Duration: 6, 10 seconds.
- Default audio: off.
- Defaults: text, 6s, 768p, 16:9. Audio: no optional audio generation.
- Credits: From 28 credits · default 6s · 768p.

### Seedance 1.0 Pro (seedance-1.0-pro)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- Prompt: required, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 2–12 (step 1) seconds.
- Default audio: off.
- Defaults: text, 5s, 1080p, 16:9. Audio: no optional audio generation.
- Credits: From 61 credits · default 5s · 1080p.

### Wan 2.5 (wan-2.5)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 1 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 1 audio files (1 total); ratios: 16:9, 9:16, 1:1.
- image mode: up to 1 images, 0 videos, 1 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 1500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 5, 10 seconds.
- Default audio: on.
- Defaults: text, 5s, 1080p, 16:9. Audio: native.
- Credits: From 75 credits · default 5s · 1080p.

### Kling 2.6 Pro (kling-2.6-pro)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 2500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 1080p.
- Duration: 5, 10 seconds.
- Default audio: on.
- Defaults: text, 5s, 1080p, 16:9. Audio: optional.
- Credits: From 70 credits · default 5s · 1080p.

### Veo 3.1 (veo-3.1)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: auto, 16:9, 9:16.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p, 1080p, 4k.
- Duration: 4, 6, 8 seconds.
- Default audio: on.
- Defaults: text, 8s, 720p, 16:9. Audio: optional.
- Credits: From 320 credits · default 8s · 720p.

### HappyHorse 1.0 (happyhorse-1.0)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1, 4:3, 3:4.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 2500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p, 1080p.
- Duration: 3–15 (step 1) seconds.
- Default audio: off.
- Defaults: text, 5s, 1080p, 16:9. Audio: no optional audio generation.
- Credits: From 140 credits · default 5s · 1080p.

### HappyHorse 1.1 (happyhorse-1.1)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 2500 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p, 1080p.
- Duration: 3–15 (step 1) seconds.
- Default audio: off.
- Defaults: text, 5s, 1080p, 16:9. Audio: no optional audio generation.
- Credits: From 90 credits · default 5s · 1080p.

### Grok Imagine 1.5 (grok-imagine-1.5)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 4096 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480p, 720p, 1080p.
- Duration: 1–15 (step 1) seconds.
- Default audio: on.
- Defaults: text, 6s, 720p, 16:9. Audio: native.
- Credits: From 84 credits · default 6s · 720p.

### H3 Max Styles (h3-max-styles)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: required, maximum 49868 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 768P.
- Duration: 5–15 (step 1) seconds.
- Default audio: on.
- Defaults: text, 5s, 768P, 16:9. Audio: native.
- Styles: hand-drawn, vhs, retro-toon-70s, low-poly, 16bit-pixel.
- Credits: From 40 credits · default 5s · 768P.

### H3 Max Camera Control (h3-max-camera-control)

- Modes: image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: inferred from input.
- Prompt: optional, maximum 50000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480P, 768P, 1080P.
- Duration: 3–15 (step 1) seconds.
- Default audio: off.
- Defaults: image, 5s, 768P, 16:9. Audio: no optional audio generation.
- Styles: orbit-right, orbit-left, push-in, pull-back, crane-up.
- Credits: From 40 credits · default 5s · 768P.

### H3 Max Lip Sync (h3-max-lip-sync)

- Modes: reference; operation: h3-lipsync.
- Input limits: 1 images, 0 videos, 1 audio files. Reference-mode requirements follow the workspace.
- reference mode: up to 1 images, 0 videos, 1 audio files (12 total); ratios: inferred from input.
- Prompt: optional, maximum 2000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480P, 768P, 1080P, 2K.
- Duration: 5 seconds.
- Default audio: on.
- Defaults: reference, 5s, 768P, adaptive. Audio: native.
- Credits: From 40 credits · default 5s input · 768P.

### Gemini Omni (gemini-omni)

- Modes: text, image.
- Input limits: 1 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 16:9, 9:16.
- image mode: up to 1 images, 0 videos, 0 audio files (1 total); ratios: 16:9, 9:16.
- Prompt: required, maximum 20000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 720p.
- Duration: 3–10 (step 1) seconds.
- Default audio: on.
- Defaults: text, 8s, 720p, 16:9. Audio: native.
- Credits: From 100 credits · default 8s · 720p.

### H3 LoRA (h3-lora)

- Modes: text, image.
- Input limits: 2 images, 0 videos, 0 audio files. Reference-mode requirements follow the workspace.
- text mode: up to 0 images, 0 videos, 0 audio files (0 total); ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
- image mode: up to 2 images, 0 videos, 0 audio files (2 total); ratios: inferred from input.
- Prompt: required, maximum 50000 characters. Text mode uses a brief; image mode needs a starting image; reference/processing modes require their source inputs as shown in the workspace.
- Resolutions: 480P, 768P, 2K, 4K.
- Duration: 5–15 (step 1) seconds.
- Default audio: on.
- Defaults: text, 5s, 768P, 16:9. Audio: native.
- Requires supplied LoRA sources; this workspace does not offer LoRA training.
- Credits: From 38 credits · default 5s · 768P.

## General image workspace

- [Open image workspace](https://uptownfunkai.com/ai-image-generator)
Quote examples state resolution and aspect-ratio conditions. Extra references, output count, quality and editing options can change the final quote.

### Seedream 5.0 Pro (seedream-5-pro)

- Modes: layer-decomposition, text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 5000 characters. Image edit mode needs an input image.
- Default resolution: 2K; maximum outputs: 6.
- Input file limit: 31,457,280 bytes.
- Layer mode needs one image without a text prompt. Resolutions: auto, 1K, 1.5K, 2K; types: image/jpeg, image/png, image/webp, image/bmp, image/tiff, image/gif.
- Resolutions: 1K, 2K.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
- Credits: Generate: 1K 7 · 2K 14 credits/image; extra edit references quoted in the workspace. Layer reserve: Auto/1K/1.5K 72 · 2K 144 credits; settles by actual layers with excess refunded.

### GPT Image 2.5 Flare (gpt-image-2.5-flare)

- Modes: text, image.
- Maximum input images: 16.
- Text/edit prompt: required, maximum 32000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 10.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto).
- Output formats: png, jpeg, webp (default png); optional editing mask. Custom image dimensions follow the workspace size validator.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5.
- Credits: 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling..

### GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst)

- Modes: text, image.
- Maximum input images: 16.
- Text/edit prompt: required, maximum 32000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 10.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto).
- Output formats: png, jpeg, webp (default png); optional editing mask. Custom image dimensions follow the workspace size validator.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5.
- Credits: 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling..

### GPT Image 2 (gpt-image-2)

- Modes: text, image.
- Maximum input images: 16.
- Text/edit prompt: required, maximum 20000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5.
- Credits: Square/auto: 1K 19 · 2K 25 · 4K 38; non-square: 1K 22 · 2K 27 · 4K 41 credits/image.

### Nano Banana 2 (nano-banana-2)

- Modes: text, image.
- Maximum input images: 14.
- Text/edit prompt: required, maximum 20000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
- Credits: 1K 8 · 2K 12 · 4K 16 credits/image.

### Nano Banana Pro (nano-banana-pro)

- Modes: text, image.
- Maximum input images: 14.
- Text/edit prompt: required, maximum 20000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
- Credits: 1K 15 · 2K 15 · 4K 30 credits/image.

### Nano Banana (nano-banana)

- Modes: text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 20000 characters. Image edit mode needs an input image.
- Default resolution: workspace default; maximum outputs: 4.
- Resolutions: workspace default.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Credits: default 4 credits/image.

### Seedream 5 Lite (seedream-5-lite)

- Modes: text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 5000 characters. Image edit mode needs an input image.
- Default resolution: 2K; maximum outputs: 4.
- Resolutions: 2K, 3K.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Credits: 2K 4 · 3K 4 credits/image.

### Seedream 4.5 (seedream-4-5)

- Modes: text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 3000 characters. Image edit mode needs an input image.
- Default resolution: 2K; maximum outputs: 4.
- Resolutions: 2K, 4K.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Credits: 2K 4 · 4K 4 credits/image.

### Seedream V4 (seedream-v4)

- Modes: text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 5000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K, 2K, 4K.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Credits: 1K 4 · 2K 4 · 4K 4 credits/image.

### Bria RMBG 2.0 (bria-background-remove)

- Modes: image.
- Maximum input images: 1.
- Text/edit prompt: optional, maximum 0 characters. Image edit mode needs an input image.
- Default resolution: original; maximum outputs: 1.
- Image types: image/jpeg, image/png, image/webp.
- Input file limit: 31,457,280 bytes.
- Resolutions: original.
- Aspect ratios: auto.
- Credits: original 4 credits/image.

### Illusion Diffusion (illusion-diffusion)

- Modes: image.
- Maximum input images: 1.
- Text/edit prompt: required, maximum 2000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 1.
- Image types: image/jpeg, image/png, image/webp.
- Input file limit: 10,485,760 bytes.
- Resolutions: 1K.
- Aspect ratios: 1:1.
- Credits: 1K 4 credits/image.

### Z-Image (z-image)

- Modes: text.
- Maximum input images: 0.
- Text/edit prompt: required, maximum 1000 characters. Image edit mode needs an input image.
- Default resolution: workspace default; maximum outputs: 1.
- Resolutions: workspace default.
- Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16.
- Credits: default 4 credits/image.

### Nano Banana 2 Lite (nano-banana-2-lite)

- Modes: text.
- Maximum input images: 0.
- Text/edit prompt: required, maximum 50000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K.
- Aspect ratios: auto, 1:1, 21:9, 16:9, 3:2, 4:3, 5:4, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8.
- Credits: 1K 5 credits/image.

### GPT Image 1.5 (gpt-image-1.5)

- Modes: text, image.
- Maximum input images: 10.
- Text/edit prompt: required, maximum 32000 characters. Image edit mode needs an input image.
- Default resolution: 1K; maximum outputs: 4.
- Resolutions: 1K.
- Aspect ratios: 1:1, 3:2, 2:3.
- Credits: 1K 14 credits/image.

## Layer decomposition and browser image utilities

- Seedream 5.0 Pro layer decomposition, auto: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 1K: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 1.5K: reserve 72 credits for up to 16 billable layers; one-layer quote 5 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Seedream 5.0 Pro layer decomposition, 2K: reserve 144 credits for up to 16 billable layers; one-layer quote 9 credits. Actual layer count determines settlement; unused reserved credits return. This is not a normal per-image generation charge.
- Browser image utilities consume 0 generation credits. Processing/history requires sign-in and verified email; inputs and outputs are saved to the account. This is separate from paid AI image models.
- [Compress Image](https://uptownfunkai.com/compress-image)
- [Resize Image](https://uptownfunkai.com/resize-image)
- [Convert Image](https://uptownfunkai.com/convert-image)
- [Rotate Image](https://uptownfunkai.com/rotate-image)
- [Crop Image](https://uptownfunkai.com/crop-image)
- [Watermark Image](https://uptownfunkai.com/watermark-image)
- [Background Remover](https://uptownfunkai.com/background-remover)
- [Transparent Background](https://uptownfunkai.com/transparent-background)
- [White Background](https://uptownfunkai.com/white-background)
- [Change Background Color](https://uptownfunkai.com/change-background-color)

- [Purchase credits](https://uptownfunkai.com/pricing.md)