Все модели

Optimizes audio files with speech

woman Flux model

Implementation of the RemBG library

Hunyuan-Video model finetuned on Dune (2021). Trigger word is "DN". Use "A video in the style of DN, DN" at the beginning of your prompt for best results.

flux.1-lite-8B-alpha by Freepik

Dreamshaper superfast generation

SOTA image-to-3D generator TRELLIS. Equipped with **All image-condition types** you need: (1) single-image (2) multi-images (3) different images for geometry and texture generation (4) mesh+images for detail variation(texture painting)

Change the strength of the prompt to enable editing style and content. Recommendation: keep the seed constant and tune the strength.

This model generates photo portraits of Court Kizer. Use the trigger word "ckizer" in your prompt. EX: "A professional portrait photo of ckizer, in a tech office in California"

Yuan2.0 is a new generation LLM developed by IEIT System, enhanced the model's understanding of semantics, mathematics, reasoning, code, knowledge, and other aspects.

[Non-commercial] Generate texture for 3D assets using text descriptions

An SDXL fine-tune based on Picasso's work

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

SDXL fine-tuned on The Nightmare Before Christmas

Filling in images quickly with Stable Diffusion and AITemplate

turns text into pdf files with TeX

Van Gogh-fy your image !! Or maybe not

ControlNet annotators - the initial image that is fed into a stable diffusion pipeline with ControlNet

An image model trained on portraits from Napoleonic era France, notably by painter François Gérard. Use FIRSTEMPIREPAINTINGS in the prompt.

Hunyuan-Video model finetuned on La La Land (2016). Trigger word is "LLLND". Use "A video in the style of LLLND, LLLND" at the beginning of your prompt for best results.

A SDXL fine-tune based on the cyberpunk style

SDVN10-Anime

Deliberate V3 Model (Text2Img, Img2Img and Inpainting)

Hunyuan-Video model finetuned on Pulp Fiction (1994). Trigger word is "PLPFC". Use "A video in the style of PLPFC, PLPFC" at the beginning of your prompt for best results.

ChatTTS is a text-to-speech model designed specifically for dialogue scenarios such as LLM assistant.

Qwen-Image configured for transparency and performance. It uses the official HuggingFace model for provenance, BF16 for numerical stability, and includes an optional Lightning LoRA. ⚠️ Each manual test = full cold boot cost!

testing dreambooth on self