Все модели
Полный список отсортирован по популярности на Replicate.
Simple tool to extract audio from a video file
A combination of ip_adapter SDv1.5 and mediapipe-face to inpaint a face
Text-guided image generation and editing
Another face swap model? 🧐 Yep, but with indexes. Swap exactly the faces you want by picking their positions. Simple, flexible, and works great on group photos.
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
Controlnet v1.1 - Tile Version
Utilize the capabilities of SD WebUI, including Hires. fix and plenty of extensions (e.g. ADetailer)
Efficient Pretraining of Text-to-Image Models
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
Stencil maker - create a black and white stencil image from any photo
A fine-tuned version SDXL for generating loteria cards
Styledreams -- CLIP x Stylegan2
Replicate model that creates a creature from a sketch.
text-to-image with latent diffusion
Latest video model from Pixverse with astonishing physics
Inpainting using Denoising Diffusion Probabilistic Models
Flux lora trained on Midjourney v3 outputs from 2022, use "a dream, in the style of MJV3" to trigger generation, also try increasing lora strength above 1
PaliGemma 3B, an open VLM by Google, pre-trained with 224*224 input images and 128 token input/output text sequences
A release preview of the olmOCR model from Ai2 that's fine tuned from Qwen2-VL-7B-Instruct using the olmOCR-mix-0225 dataset
Professional PNG to SVG vectorization with VTracer. Lightning-fast conversion with superior quality.
Image Inpainting
Photo to cartoon translation
The Yi series models are large language models trained from scratch by developers at 01.AI.
SOTA image model from xAI
Flux lora, use "ps1 game screenshot" to trigger image generation
SDXL using DeepCache
Generate images quickly with GLID-3 (non-xl)
Ollama Llama 3.2 Vision 11B
Learning Adapters towards Controllable for Text-to-Image Diffusion Models
SDXL fine-tuned on black light imagery
A 13 billion parameter Llama tuned for coding with Python
Flux trained on QFACES of High quality facial textures of diverse people, age, ethnicity. Mainly used for image to image (img2img) enhancement. See Readme for ideas & settings.
This is the fastest sdxl-lightning endpoint in the world on A100, contact us for more at pruna.ai
Compose a song from a prompt or a composition plan
Ollama Llama 3.2 Vision 90B
Kandinsky Image Generation with ControlNet Conditioning
Dreamlike Photoreal Model for Splurge Art
Meta Llama 3.2 1B
GLIDE from OpenAI finetuned on roughly 30M more samples. See `laionide-v3` for the latest.
SDXL model trained on a blocky oil painting and still life.
Text-to-gif using SDXL, with controlnet and lora support
Cut and Learn for unsupervised object detection and instance segmentation
A flux lora for panoramas, use 21:9 and "HDRI panoramic view of TOK" to trigger image generation