Все модели

Voxtral builds upon Ministral-3B with powerful audio understanding capabilities

Be sure to start the prompt with "A drawing of MDBEAR, ". Use a guidance scale value of 3.5. Experiment with the LoRA scale, 1.2 seems to work well

The model trained based on Olga Ciob's drawing during a workshops in Bucharest.

Segments the wall, door, window, and kitchen of the floor plan image

Ugly Sweaters: The only garment that screams "Fashion? Never heard of it."

A stable diffusion model trained on pictures from my buddy Toshiro (truly the best boy there is)

Hunyuan-Video model finetuned on The Matrix Trilogy (1999). Trigger word is "THMTR". Use "A video in the style of THMTR, THMTR" at the beginning of your prompt for best results.

SDXL fine-tuned on paper collages

A 8k sequence length text embedding set trained by Jina AI

繁花 style 测试

PartCrafter is a structured 3D mesh generation model that creates multiple parts and objects from a single RGB image.

Generates Photo Daddies

A project that I recycled for many of my classes as their Final Project assignments.

A style that creates a paint wash, great for anime.

A style model, ligne claire esque with eastern influence

Generate images in the style of Batman The Animated Series

Minimal and Universal Control for Diffusion Transformer - demo for Spatially aligned control

Generate petitions suitable for sending to the UK government

Flat Eric is a puppet character

A Hunyuan fine-tuned on the Homer disappearing into a bush meme

Improved Distribution Matching Distillation for Fast Image Synthesis

Denoiser from Resemble