Все модели
Полный список отсортирован по популярности на Replicate.
An SDXL fine-tune based on the Labyrinth movie
SDXL finetune to generate curvy minimalist shapes and patterns. WIP . Trained on AI generated images that had South Indian alphabets as central motif in prompts to achieve satisfactory rotundness.
AnimateDiff video to video
Multi stage image editing of images using stable-diffusion with a mask and a prompt
Transform any product photo into professional 2000x2000px packshots with optimal positioning
SoTA depth estimation
The Emergence Image Generation model for the Shard faction.
Creates voxels like game asset
SDXL model trained onon iconic Italian posters from the '60s.
Dream-girl Sydney Sweeney ready for your creative liberties!
DPO-SDXL Canny controlnet with LoRA support.
OpenFLUX.1 (Beta v0.1.0), is a fine tune of the FLUX.1-Schnell model with the distillation trained out of it
Flux then and now photograph comparison lora
Erase what you don't want on your image
I been making Ai music and keep trying to end the song and waste alot of credits, so instead i just coded a audio trimmer with a fade last 2.5 seconds options ha. Enjoy!
Generate detailed mobile app user interfaces (UIs) using prefix “MOBIUI containing..” in 4-15 steps.
Generate an image by specifying a different text prompt for each region
Replicate model that creates a paper-mini image with an illustrated artstyle.
WizardCoder-python-34B-v1.0 with support for grammars and jsonschema
Fast Segmind-Vega with 2-8 inference steps.
Microsoft's VibeVoice text-to-speech model that can generate long-form speech from text with sample voices.
a FLUX.1 [dev] lora of Mark Henry's face
Shows what CLIP looks at in an image given text
Add a customizable watermark to any video with a simple API call. Used in the video AI creator at UGCMade.com and brought to you by your friends at Megacubos.com.
Train on RealVisXL 4.0 (Realistic Vision XL 4) | Mixed precision bf16 any LoRA
Image Caption model
DreamBooth safetensors model use RealVisXL
Llama-2 13B with support for grammars and jsonschema
Flux lora, use “WRNG” to trigger image generation
Prompt-free Diffusion
Modelo entrenado para que haga dibujos estilo Liniers
ComfyUI API
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
AnimateDiff v3 + SparseCtrl: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. Created with Shimmer.
This is an ML model to segment hairs in pictures.
Fast image variation model
A small language model for tasks like classification, summarization, and more.
A fine-tuned SDXL LoRA trained on images from World War 2