Model reference · open weights

HDM-xut-anime

Available as managed deployment Licence fee Image KBlueLeaf · community Text→image 1 variants 877 dl/mo

HDM-xut-anime is an open-weight image model from KBlueLeaf. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byKBlueLeaf
TypeImage models
TaskText→image
Parameters (lead)343M
Runs withdiffusers
Released2025-08-13
Popularity877 downloads / month
LicenceCommercial licence needed

About

What HDM-xut-anime is

World's smallest, cheapest anime-style T2I base

-2ea44f) -HDM-2ea44f)

Introduction

HDM(Home made Diffusion Model) is a project to investigate specialized training recipe/scheme for "pretraining T2I model at home" which require the training setup should be exectuable on customer level hardware or cheap enough second handed server hardware.

Under this constraint, we introduce a new transformer backbone designed for multi-modal (for example, text-to-image) generative model called "XUT" (Cross-U-Transformer). With minimalized arch design with TREAD technique, we can achieve usable performan with computes that cost 650USD at most. (based on pricing from vast.ai)

Read the full model card

Gallery

.gallery-container { position: relative; width: 100%; margin: 0 auto; font-family: Arial, sans-serif; } .gallery-container img{ margin: 0 !important; padding: 0 !important; }

/* Hide radio buttons */ .gallery-container input[type="radio"] { display: none; }

/* Thumbnail navigation */ .thumbnail-nav { display: flex; align-items: center; gap: 12px; margin-bottom: 20px; padding: 10px; overflow-x: auto; scroll-behavior: smooth; scroll-snap-type: x mandatory; -webkit-overflow-scrolling: touch; scrollbar-width: thin; scrollbar-color: #B398F5 #f0f0f0; }

/* Custom scrollbar for webkit browsers */ .thumbnail-nav::-webkit-scrollbar { height: 6px; }

.thumbnail-nav::-webkit-scrollbar-track { background: #f0f0f0; border-radius: 3px; }

.thumbnail-nav::-webkit-scrollbar-thumb { background: #B398F5; border-radius: 3px; }

.thumbnail-nav::-webkit-scrollbar-thumb:hover { background: #4C88F5; }

.thumbnail-nav label { width: 100px; height: 120px; border-radius: 8px; background-color: #B398F5; background-size: cover; background-position: center; cursor: pointer; transition: all 0.3s ease; display: block; flex-shrink: 0; scroll-snap-align: center; position: relative; overflow: hidden; padding: 0; }

/* Blurred background for thumbnails */ .thumbnail-nav label::before { content: ''; position: absolute; top: 0; left: 0; width: 100%; height: 100%; background-image: inherit; background-size: cover; background-position: center; background-repeat: no-repeat; filter: blur(2px) brightness(25%); transform: scale(1.25); z-index: 1; }

/* Fitted image for thumbnails */ .thumbnail-nav label::after { content: ''; position: absolute; top: 50%; left: 50%; transform: translate(-50%, -50%); width: 100%; height: 100%; background-image: inherit; background-size: contain; background-position: center; background-repeat: no-repeat; z-index: 2; }

.thumbnail-nav label:hover { border-color: #4C88F5; transform: scale(1.05); }

.gallery-container input[type="radio"]:checked + label { border-color: #6296F5; border-width: 4px; transform: scale(1.1); }

/* Main content area */ .content-area { position: relative; width: 100%; min-height: 780px; border-radius: 10px; overflow: hidden; box-shadow: 0 4px 15px rgba(0,0,0,0.1); }

/* Individual slide containers */ .slide { position: absolute; top: 0; left: 0; width: 100%; height: 100%; opacity: 0; visibility: hidden; transition: opacity 0.5s ease; background: white; }

.slide.active { opacity: 1; visibility: visible; }

.slide-background-image { width: 100%; height: 480px; object-fit: cover; border-radius: 10px 10px 0 0; filter: blur(3px) brightness(25%); transform: scale(1.1); position: absolute; top: 0; left: 0; z-index: 1; margin: 0 !important; padding: 0 !important; }

/* Container for the image area */ .slide-image-container { position: relative; width: 100%; height: 480px; overflow: hidden; border-radius: 10px 10px 0 0; }

/* Fitted image overlay */ .slide-fitted-image { position: absolute; top: 50%; left: 50%; transform: translate(-50%, -50%); max-width: 100%; max-height: 100%; object-fit: contain; z-index: 5; box-shadow: 0 2px 10px rgba(0,0,0,0.3); margin: 0 !important; padding: 0 !important; }

.slide-content { height: 300px; padding: 20px; flex-grow: 1; background-color: #21203b; overflow-y: scroll; }

.slide-title { font-size: 1.5em; font-weight: bold; margin-bottom: 10px; color: #eee; }

.slide-description { color: #aaa; /* line-height: 1.6; */ }

/* CSS selectors to show active slides */ #slide1:checked ~ .content-area .slide:nth-child(1), #slide2:checked ~ .content-area .slide:nth-child(2), #slide3:checked ~ .content-area .slide:nth-child(3), #slide4:checked ~ .content-area .slide:nth-child(4), #slide5:checked ~ .content-area .slide:nth-child(5), #slide6:checked ~ .content-area .slide:nth-child(6), #slide7:checked ~ .content-area .slide:nth-child(7), #slide8:checked ~ .content-area .slide:nth-child(8), #slide9:checked ~ .content-area .slide:nth-child(9), #slide10:checked ~ .content-area .slide:nth-child(10), #slide11:checked ~ .content-area .slide:nth-child(11), #slide12:checked ~ .content-area .slide:nth-child(12), #slide13:checked ~ .content-area .slide:nth-child(13), #slide14:checked ~ .content-area .slide:nth-child(14), #slide15:checked ~ .content-area .slide:nth-child(15), #slide16:checked ~ .content-area .slide:nth-child(16), #slide17:checked ~ .content-area .slide:nth-child(17), #slide18:checked ~ .content-area .slide:nth-child(18), #slide19:checked ~ .content-area .slide:nth-child(19), #slide20:checked ~ .content-area .slide:nth-child(20), #slide21:checked ~ .cont

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys hdm-xut-anime for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hdm-xut-anime below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hdm-xut-anime","prompt":"a red bicycle","size":"1024x1024"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms