Все модели
Полный список отсортирован по популярности на Replicate.
Flux fine-tuned on the art of William Blake
Llama2 70B with embedding output
Img2Img diffusion in the style of Van Gogh
Create your own courtroom sketch painting style images
Combines inpainting and outpainting for image editing.
Creates Outputs in the Style of Backyard Sports Characters
视频识别自动分割场景
Simple binary sentiment analysis with BERT
Dkamacho’s Scene Assembler
For the paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
SDXL tuned on Anatoly Fomenko paintings
Generate Casual Socks for your Theme
Modify an existing video through natural-language commands, changing subjects, environments, and visual style while preserving the original motion and timing.
MT3: Multi-Task Multitrack Music Transcription
An SDXL fine-tune based on Junji Ito's manga drawings
Creates an SD illusion from drawing + adds depth
Fine-tunable Qwen Image model with exceptional composition abilities - train custom LoRAs for any style or subject
i2v-14B-720p-2.1
A 6B parameter open bilingual chat LLM (optimized for 8k+ context) | 开源双语对话语言模型
I found this cool audio wave generator and made it my own.
musicgen small fine tuned on an edm dataset
Turn two prompts into one image
SDXL fine-tuned on 100s of manually colorized historical photos
A fine-tuned FLUX.1 model. Use trigger word "ZUCK". Created with ReFlux (https://reflux.replicate.dev).