# High-Resolution Generation

LoRA weights trained for THUDM/CogVideoX-5b-I2V, designed for image-to-video tasks

Hierarchical Distillation (SwD) is a novel framework that accelerates diffusion models (DMs) by progressively increasing spatial resolution during the generation process.

Hunyuan Video-I2V is a novel image-to-video generation framework, extended from Tencent's Hunyuan Video model, supporting high-quality video generation from static images.

INT4 quantized version of FLUX.1-Fill-dev, capable of filling regions in existing images based on text descriptions, providing approximately 4x memory savings and 2-3x speed improvements.

doa is a text-to-image generation project created based on the SDXL model, developed by reijlita, which can achieve high-quality text-to-image conversion.

A GLIGEN adapter supporting the SDXL version, providing HuggingFace-style pipelines for text-to-image generation tasks.

Stable Diffusion is a text-to-image diffusion model capable of generating high-quality images from text descriptions.

JanusFlow is a powerful framework that unifies image understanding and generation in a single model, combining autoregressive language models with rectified flow methods.

A text-to-image generation model based on Stable Diffusion XL (SDXL), supporting ControlNet functionality.

Flux-Dev2Pro is a text-to-image generation model based on the diffusers library, capable of producing high-quality images from textual descriptions.

FLUX.1-dev is a text-to-image generation model based on black-forest-labs/FLUX.1-schnell, specializing in dark fantasy-style image generation with grainy effects.

FLUX.1-dev is a text-to-image generation model based on the diffusers library, focusing on high-quality image synthesis.

LoRA fine-tuned version based on FLUX.1-dev model, specializing in TSTVCTR vector art style image generation

CogVideoX is an open-source video generation model originating from Qingying. This version is a dedicated image-to-video model based on a 5B parameter scale.

CogVideoX is the open-source version of the video generation model from Qingying. The 2B version is an entry-level model that balances compatibility with low operational and development costs.

A latent diffusion model for text-to-image generation, supporting 512x512 resolution image generation

LinFusion is a text-to-image generation model based on diffusion models, capable of producing high-quality images from textual descriptions.

Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images from any text input.

Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images from text inputs.

A text-to-image generation system based on latent diffusion models, capable of producing high-quality images from text prompts

FLUX.1 development version LoRa model, designed specifically for generating panoramic search illustrations in the style of 'Where's Waldo'

FLUX.1-dev is a text-to-image diffusion model quantized to INT8 format using Optimum Quanto, suitable for non-commercial use.

All-in-one ControlNet model supporting 12 control conditions and 5 advanced editing features for integrated image generation and editing

An advanced latent text-to-image diffusion model optimized based on Stable Diffusion XL 1.0, specializing in generating high-resolution anime images

T2I Adapters are networks that provide additional conditional control for stable diffusion models. This checkpoint is specifically designed to provide depth condition control for StableDiffusionXL.

A diffusion-based text-to-image generation model that supports generating and editing high-quality images through text prompts

Diffusers is a diffusion model library for image generation, supporting various pre-trained models and custom training.

Stable Diffusion is a diffusion model for text-to-image generation, capable of producing high-quality images based on textual descriptions.

Stable Diffusion is a text-to-image generation model based on diffusion models, capable of producing high-quality images from textual descriptions.

Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images from any text input.

A diffusion-based text-to-image generation model capable of producing realistic images from text prompts

Text-to-image generation technology based on latent diffusion models, capable of generating realistic images from text input