Skip to content
Sample image made with AnimaYume
Anima Image Local Cloud Image input

AnimaYume

AnimaYume is an anime image model for bright, clean characters with firm lines and glossy light. Strong at portraits, pairs, and sunny exteriors. Good pick for posters, VTuber fan art, and slice of life scenes. Run it free on your GPU in Imference Desktop or call it by API.

$0.005

per image in the cloud

$0

on your own GPU

Good at

  • Single characters and small groups, readable hands, tidy silhouettes.
  • Two looks: punchy cel shading with sparkles, or soft gradient lighting with bounce light.
  • Outdoor scenes with backlight and rim light, glossy hair and fabric, blue coasts and warm rooftops.
  • Light fantasy details like halos or wings without breaking composition.

Running it

  • Runs local in Imference Desktop, 4.2 GB download, part of the Anima family.
  • Also available in the cloud by REST API, no download, same outputs across both.
  • Accepts an input image for pose, color, or layout guidance.
  • Model code is animayume, use this in the API or the Imference MCP server.

Prompting it

  • Use comma-separated tags in short clauses: "girl, three-quarter view, bright sun, seaside town, glossy highlights, wings".
  • Defaults are tuned: steps 30, guidance 5.5, API users can set them if needed.
  • Lighting and color tags steer it well: "golden hour, backlit, rim light, pastel sky, cyan orange".
  • Composition and style tags: "close-up portrait, group on couch, cel shading, painterly anime, thick outlines".

Use it

Three ways to run AnimaYume

Local · free

  1. Open Imference Desktop and stay on Local.
  2. In Local models, pick AnimaYume. It downloads once.
  3. Write a prompt and press Generate. It runs on your GPU.

Cloud · $0.005 per image

  1. Open Imference Desktop and switch to Cloud.
  2. Buy credits by card: your Imference key is created for you.
  3. Pick AnimaYume and press Generate. Nothing to download.

In your browser · $0.005 per image

  1. Open Imference Web. Nothing to install, no account.
  2. In Cloud model, pick AnimaYume.
  3. Write a prompt and press Generate. Buy credits by card the first time, no account.
Make an image with AnimaYume ("animayume"): a lighthouse on a cliff at dusk, cinematic light

Claude needs the MCP server.

Specs

The details

Price
$0.005 · 5 credits
$5 buys
1,000 images
Prompt style
Tags
Runs
Local and cloud
Default steps
30
Default CFG
5.5
Reference images
Up to 1
Model code
animayume

Formats

Square

1024×1024

Portrait

896×1152

Landscape

1152×896

Portrait Large

832×1216

Landscape Large

1216×832

Portrait Wide

768×1344

Landscape Wide

1344×768

Portrait Ultra-Wide

640×1536

Landscape Ultra-Wide

1536×640

LoRAs

Styles that work with it

Sample of the Anime Flat Style LoRA
Anime Flat Style
Sample of the Anime in real LoRA
Anime in real
Sample of the Dark Art Style LoRA
Dark Art Style
Sample of the Detail Tweaker LoRA
Detail Tweaker
Sample of the Retro Sci-fi 90's an LoRA
Retro Sci-fi 90's an
Sample of the Velvet's Mythic Fant LoRA
Velvet's Mythic Fant

Similar

You might also like

All 85 models

Try AnimaYume tonight