epiCRealism v7-Final Destination. Top Realism Model on Civitai

blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1, The top ranked model on Civitai

This is an implementation of the ChatTTS as a Cog model.

Stylized Audio-Driven Single Image Talking Face Animation

Recreate images with Emojis

Fast and High-Quality Text-to-video Generation

A PhotoBooth style transfer workflow that utilizes IPadapter Style, Canny, OpenPose, RemoveBackground, HumanSegmentation, Cloth Segmentation for initial input, and concludes with the application of DeepFake techniques.

AI Photorealistic Image Ultra-Resolution, Restoration and Upscale!

SDXL LoRA finetuned on spectrograms of Beethoven songs

Transfer empty room into fabulous interior design

Guided Text to Speech Generator

viⓍTTS vixTTS là mô hình tạo sinh giọng nói cho phép bạn sao chép giọng nói sang các ngôn ngữ khác nhau chỉ bằng cách sử dụng một đoạn âm thanh nhanh dài 6 giây

Given image of an face, the it generates full images with given prompt

Jina Turbo Reranker that is small but performant

SDXL based text-to-image model applying Distribution Matching Distillation, supporting zero-shot identity generation in 2-5s. https://ai-visionboard.com

Fast sdxl with higher quality

for test

A text-to-image generative AI model that creates beautiful images

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Use a face to make images. Uses SDXL fine-tuned checkpoints.

This is phi-3-vision model , cost by time ,have fun~

Convert story to StableDiffusion prompts format

openai whisper model on A100 hardware

Image tagger fine-tuned on WaifuDiffusion w/ (SwinV2, SwinV2, ConvNext, and ViT)

✍️✨Prompts to auto-magically relights your images

Replicate version from the work of Shanglin Li et al. called "ZONE: Zero-Shot Instruction-Guided Local Editing"

🖼️✨Background images + prompts to auto-magically relights your images (+normal maps🗺️)

This is an ML model to segment hairs in pictures.

Segment foreground objects with high resolution and matting, using InSPyReNet

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Three models in one Cog: Absolute Reality v1.8.1, DreamShaper v8 and Meina V4

Source: gradientai/Llama-3-8B-Instruct-Gradient-4194k ✦ Quant: solidrust/Llama-3-8B-Instruct-Gradient-4194k-AWQ ✦ Extending LLama-3 8B's context length from 8k to 4194K

CLIP Interrogator for SDXL optimizes text prompts to match a given image

📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment

An example model created from cli

PaliGemma 3B, an open VLM by Google, pre-trained with 224*224 input images and 128 token input/output text sequences

A model which generates text in response to an input image and prompt.

Generate image with transparent background

Yi-1.5 is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view LRMs

Blip 3 / XGen-MM, Answers questions about images ({blip3,xgen-mm}-phi3-mini-base-r-v1)

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.

return CLIP features for the dfn5b-clip-vit-h-14-384, current highest average perf. in openclip models leaderboard.

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.