Все модели
Полный список отсортирован по популярности на Replicate.
Flux Dev diffusers implementation
Tuning-free Higher-Resolution Visual Generation with Diffusion Models
👀 SDXL fine-tune to add googly eyes to anything
klkl\]\
CodeLlama-34B-instruct with support for grammars and jsonschema
MEMO is a state-of-the-art open-weight model for audio-driven talking video generation.
赤羽全域のモデルです！最新版なのでこちらをお使いください！
This Adds Background Music & Prefect subtitles from json file
full body version
Transform PDFs into AI podcasts for engaging on-the-go audio content.
Flux finetune that is trained on Glitches generated by a Processing Script ( In Readme ), WIP.
Fusion – Product/object blending that fixes perspective and lighting so the subject melts into a new background via the Fusion LoRA.
Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
SDXL fine-tuned on pareidolia
MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation.
Pose estimation with OpenPose
Flux dev lora trained on photos of 1970s food
Kimi-VL-A3B-Thinking is a multi-modal LLM that can understand text and images, and generate text with thinking processes
Generate equirectangular images with Stable Diffusion.
album cover generator
Stable Diffusion Meets Karlo: a combination of the Karlo CLIP image embedding prior, and Stable Diffusion v2.1-768.
Chatterbox is a state-of-the-art zeroshot TTS
Unified Model for Image, Video, Audio and Language Tasks
Consistent view characters with ControlNet and Stable Diffusion fine-tuned on Ready Player Me characters based on OpenJourneyV4
Generate videos by interpolating the latent space of Stable Diffusion
Flux lora, trained on macro textures, use "MCROTX" to trigger image generation
NoirVisions is a text-to-image AI model created by Boss Luxe, designed to generate soft, airbrushed, high-fashion digital portraits centering Black women. Trained exclusively on original, curated imagery, this model captures luxury, melanin-rich beauty, a
Scaling-up Disentanglement for Image Translation
Fine-tuned GPT-J 6B model on the Alpaca dataset
SDXL tuned on Vsevolod Ivanov paintings
sdxl trained on bobs burgers
A model using microsoft/Florence-2-large to create mask of watermarked images
Cartoon Derek is happy, sometimes
Tadanori Yokoo (横尾 忠則, Yokoo Tadanori, born 27 June 1936) is a Japanese graphic designer, illustrator, printmaker and painter. Yokoo’s signature style of psychedelia and pastiche engages a wide span of modern visual and cultural phenomena from Japan and a
Chinese Stable diffusion model
BLIP2 model trained on blip2-flan-t5-xl-coco dataset
A stylized poster style for text-to-image