# Text-to-image generation

A version of black-forest-labs/FLUX.1-Canny-dev that uses the DFloat11 format for lossless compression, which can reduce GPU memory consumption by approximately 30% while maintaining bitwise identical outputs to the original model.

A text-to-image generation model created using the Karcher mean merging method, which can convert text descriptions into images.

Maxwellill is a text-to-image generation model based on Stable Diffusion 3.5 large, supporting fine-tuning with LoRA technology.

DMM is a score distillation-based model fusion paradigm that compresses multiple pre-trained models from different domains into a versatile text-to-image generation model.

LoRA fine-tuned model based on FLUX.1-dev for text-to-image generation

LoRA fine-tuned model based on FLUX.1-dev for generating images with specific styles

This is a LoRA adaptation weight based on Stable Diffusion XL for generating Van Gogh-style images.

LoRA adapter trained on FLUX.1-dev model for text-to-image generation

A text-to-image diffusion model based on LoRA technology, combining the features of DALL-E 3 and FLUX.1-dev for generating high-quality images.

VARGPT is a unified multimodal model that combines visual understanding and generation capabilities, achieving understanding by predicting the next token and generation by predicting the next scale.

LoRA fine-tuned model based on FLUX.1-dev for text-to-image generation

LoRA model trained on FLUX.1-dev for generating images with specific styles

Childv2 is a LoRA adapter trained on the FLUX.1-dev model for text-to-image generation tasks.

This is a direct GGUF format conversion of fal/AuraFlow-v0.3, primarily used for text-to-image generation tasks.

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

8-step distilled LoRa based on FLUX.1-dev model for accelerating text-to-image generation

This is a LoRA model fine-tuned based on black-forest-labs/FLUX.1-dev, specifically designed for generating images in the style of ancient book illustrations.

A quantized version based on the RealFlux 1.0b Schnell model, focusing on text-to-image generation tasks, containing only the UNet module and supporting multiple quantization levels.

A LoRA model for text-to-image generation based on a specific style, inspired by propaganda posters, capable of generating artistic, illustrative, or cartoon images with a unique style.

A text-to-image generation model based on Stable Diffusion and LoRA technology, specializing in creating photography with a 1970s retro style.

A text-to-image generation model based on LoRA training, specializing in generating images with a rough children's illustration style.

A text-to-image generation model based on the diffusers library, which uses a nested diffusion structure to achieve high-quality image generation.

LoRA model trained based on FLUX.1-dev model for generating 3D style images

The .gguf quantized version of FLUX.1-schnell for text-to-image conversion tasks

CSBW_Style is a model based on text-to-image technology, combining technologies such as Stable Diffusion and LoRA, which can generate images in a specific style.

A text-to-image generation model based on stable diffusion technology that can generate high-quality images according to text descriptions.

This is a text-to-image generation model based on Stable Diffusion, capable of generating high-quality images according to text descriptions.

A text-to-image latent diffusion model optimized for Apple chips in Core ML format

A text-to-image model based on latent diffusion, in Core ML format optimized for Apple Silicon hardware

Text-to-image diffusion model based on Katsushika Hokusai's art style, fine-tuned using Dreambooth technology

A text-to-image generation model trained on Telltale game art assets, capable of producing 3D-stylized 2D comic content

This is a text-to-image generation model fine-tuned using Dreambooth technology based on Stable Diffusion v1-5, capable of generating images of specific concepts from text prompts.

A high-quality 3D style text-to-image model fine-tuned from Stable Diffusion 2.0, with 768x768 resolution. Use 'redshift style' in prompts to trigger the effect

A text-to-image generation model based on RunwayML 1.5 with updated VAE, specialized in generating South Park-style images.

A stable diffusion model optimized for high-resolution image synthesis, fine-tuned based on Stable Diffusion v1.5, supporting 768x768 resolution image generation

A Stable Diffusion model fine-tuned for Naruto style, capable of converting input text into Naruto-style images

A Stable Diffusion model fine-tuned on screenshots from the TV series 'Archer', capable of generating corresponding style images using the prompt tag '_archer style_'.