Все модели
Полный список отсортирован по популярности на Replicate.
This model is an optimised version of stable-diffusion by stability AI that is 3x faster and 3x cheaper.
SDXL LoRA. Trained on SDXL generations with a funky glitch aesthetic. No artists were referenced. Not Another Model Mimicking Exhausted Hues
A language model for tasks like classification, summarization, and more.
Add an image and a song and generate a video
Get image quality scores
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
A wrapper around bel-tts
A fast high quality SD 1.5 model, Realistic Vision V6.0 B1 Hyper
Domain Consistent Resolution Adapter for Diffusion Models: generating consistent images with resolutions outside of their trained domain
Qwen2 57 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to go against other general purpose models and pipelines like Midjourney and DALL-E.
WIP - For as the neon nights beget dayglo days, Glitch doth glitch the glitched, a jumble-jam, a kerfuffle of kilobytes.
MusicGen running on an a40 with 60 seconds max duration
Tileable Stable Diffusion XL
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
FLUX.1 [dev] trained on the Replicate goo
Flux finetune trained on Syd Mead concept art for Blade Runner
Trained on iPhone photos of Tokyo. Add "shot on TOKSTYL camera" at the end of your prompts.
SDXL fine-tuned on Soviet propaganda posters
High-precision video upscaler optimized for portraits, faces and products. One of the upscale modes powered by Clarity AI. X:https://x.com/philz1337x
OpenOrca-Platypus2-13B is a merge of garage-bAInd/Platypus2-13B and Open-Orca/OpenOrcaxOpenChat-Preview2-13B.
Guide Style Transfer with CLIP loss
SDXL fine-tuned on Pixar Cars
Create avatar videos with realistic humans, animals, cartoons, or stylized characters
Diffusion Models for Image Morphing
API for enhanced word-level timestamp accuracy using OpenAI's Whisper model
An SDXL fine-tune based on Deep Dream
Flux lora, use "frstingln illustration" to trigger the image generation
Flux lora, use "1980s anime screengrab", "VHS quality", or "syntheticanime" to trigger image generation
Use trained LoRAs from the https://replicate.com/prunaai/p-image-edit-trainer. Find or contribute LoRAs here: https://huggingface.co/collections/PrunaAI/p-image-edit-loras.
Generate texture for your mesh with text prompts
Wan 2.1 1.3b Video to Video. Wan is a powerful visual generation model developed by Tongyi Lab of Alibaba Group
Upscale – Detail-loving upscale/restore pass that sharpens textures and color fidelity with the Upscale LoRA.
Generates multi-view optical illusions
My own personal https://replicate.com/replicate/dreambooth
A good anime merge from 12 other models
👗Bytedance's DreamO: unified image customization model (IP, ID, Style, Try-On, etc.)🧣
SDXL fine-tune of Star Trek Next Generation interiors