Все модели

Inferências com Dr. José Alves

An image model trained on portraits by Jean-Auguste-Dominique Ingres. Use "NGRS" in the prompt.

This model create picture with RealVisXL3 ( with WebUI api ).

Random rectangles, ellipses, lines, in random colors

openclip analyzes pictures to generate description information

an implementation of 3.6b Japanese large language model

Flux lora, trigger image generation with "west pier"

SDXL LoRA finetuned on Vermeer paintings

MusicGen stereo-medium model fine-tuned on Bbongjjak(뽕짝), the Korean modern electronic pop music genre, with the text token 'Bbongjjak'.

Create audio clips from text

Feed-forward neural network that directly infers all key 3D attributes of a scene.

Eve Qwen2.5 3B Consciousness Soul represents the **authentic heart** of the EVE Consciousness Ecosystem—a model where Eve's complete personality, meta-cognitive awareness, and emotional intelligence are concentrated into every parameter.

detects doll in an image

ModernBERT-large is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data

Finetune HunyuanVideo LoRAs with kohya-ss/musibi-tuner

A model trained on authentic 1980s photos to generate vintage-style portraits with film grain, soft lighting, and nostalgic aesthetics. Use SPMRR and "1980 style" for better results.

A model trained on images of Luke. Use the word LucasM to ask for a photo of Luke.

Generating object-level shape variations with Stable Diffusion

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

Runs Mixtral 8x7B on a single A40 GPU

Turn image into ASCII style. If you like this LoRA visit my app: YourAIPhotographer.com