Все модели
Полный список отсортирован по популярности на Replicate.
Flux lora, use "in the style of FNTSYRCH" to trigger
Bielik-11B-v2.3-Instruct is a generative text model made by SpeakLeash and Cyfronet featuring 11 billion parameters. It is a linear merge of the Bielik-11B-v2.0-Instruct, Bielik-11B-v2.1-Instruct, and Bielik-11B-v2.2-Instruct models.
Fast text2image model
A pixray tool for 24x24 pixelart
Ollama Reflection 70b
A wrapper model for captioning multiple images using GPT, Claude or Gemini, useful for lora training
0.5B
Use trained LoRAs from the https://replicate.com/prunaai/p-image-trainer. Find or contribute LoRAs here https://huggingface.co/collections/PrunaAI/p-image-loras
A test of an already existing sdxl cog project to study, try, share.
Scribbled art drawings style
Fish Speech V1.5-SOTA Open Source TTS
DeepSeek-VL2-small, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL
An SDXL model Finetuned for style on Marker-Style Sketches
SoTA Zero Shot Voice Cloning and TTS model
SDXL fine tuned for sketch output style
A hand drawn sketch style LoRA
Image-Prompt Multi-view Diffusion for 3D Generation
test
Take any shot and edit specific sections. Rephrase, change the action, camera angles and more
Flux lora, use "yarn art style" to trigger image generation
A Llama-3.2-11B pretrained model, fine-tuned for content safety classification
Flawless Text is a high-precision text-to-image model that generates typo-free, visually accurate images from text descriptions, ideal for seamless, error-free creative workflows.
SigLIP proposes to replace the loss function used in CLIP by a simple pairwise sigmoid loss
Loves to wear nice Suits.
Geometry-Aware 3D Full-Head Synthesis in 360 degrees
Panoptic Scene Graph Generation
SDXL model trained on Blade Runner 2049 still frames
phixtral-2x2_8 is the first Mixure of Experts (MoE) made with two microsoft/phi-2 models, inspired by the mistralai/Mixtral-8x7B-v0.1 architecture
A Glow-based Waveform Generative Model for Audio Super-Resolution. Intelligently upsamples audio by 2x resolution
A F5-TTS fine-tuned for Spanish
Flux fine-tuned on JWST deep space astrophotography
Flux lora in a realistic film style. Use flmft photo style to trigger the image generation.
Trained on images of a real cat
Make your video talk anything
AI-Powered Gym Goddess Generator
lexi model
Interior Design with RealVisXL V5.0-Lightning and ControlNet to generate photorealistic, high-resolution interior designs.
flux-autumn-green works great with light pastel color tones, it's got a lighthearted moebius vibe.
Plugging Visual Controls in Text Generation