Text-to-Image History
How Text-to-Image evolved on HF and inspired the Community
- Running on Zero45👁
playgroundai/playground-v2.5-1024px-aesthetic
Text-to-Image • Updated • 119k • 540- Running on Zero439⚡
SDXL Lightning
Super-fast image generation on SDX
- Running on Zero1.45k👁
Stable Cascade
- Runtime error40🐨
Style-aligned Sdxl
- Running on Zero283🔍🕵️
Enhance This DemoFusion SDXL
Creative Upscaler High-Res Image Generation DemoFusion SDXL
- Running on Zero366🌍
Playground V2
- Running on Zero122🎲
LoRA Roulette
- Sleeping185🙃
Upside-Down-Diffusion
- Running on Zero3.84k👁
IllusionDiffusion
Generate stunning high quality illusion artwork
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Paper • 2309.06380 • Published • 32- Running on A10G388🌍
Wuerstchen
warp-ai/wuerstchen
Text-to-Image • Updated • 1.84k • 168- Running on A10G226🚀
T2I Adapter SDXL Sketch
- Running on A10G272🚀
T2I-Adapter-SDXL
stabilityai/control-lora
Text-to-Image • Updated • 792- Running on A10G319🔥
SDXL Inpainting
- Running on CPU Upgrade6.53k👩🎨
AI Comic Factory
Create your own AI comic with a single prompt
- Running on A100846🔎 🖼️
LoRA the Explorer
- Running on Zero341🌍
SDXL
text-to-image
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • Updated • 4.72M • 5.15k- Paused102🧘
Fooocus
- Running on A10G390✏️
LEDITS
- Running14😻
Kandinsky 2.2
text-to-image
- Paused1.49k🔥
IF
Running on T4354👥⚙️🎨Stable Diffusion Multiplayer
Note This project is an open interactive art canvas
Runtime error115💬🔀Prompt Converter
Note This demo was useful to convert SD 1.x prompts syntax to SD 2.x syntax
Running on T41.08k🕵️♂️🕵️♂️CLIP Interrogator 2
Note Same as v.1 but compatible with Stable Diffusion 2
- Running on CPU Upgrade10.3k🔥
Stable Diffusion 2-1
stabilityai/stable-diffusion-2
Text-to-Image • Updated • 292k • 1.78klllyasviel/ControlNet
Updated • 3.48k- Running on A10G255🌍
Rich Text To Image
Running466🖼️Diffusers Gallery
Note The Diffusers Gallery is a library of fine-tuned models on custom and well-know style, trained with Dreambooth, and later LoRa
Running483☁️Dreambooth Training
Note Big milestone! Dreambooth finally allowed to easily train custom styles and concepts, fast and cheap.
Running on A10G825♾️Stablediffusion Infinity
Note Outpainting !
Running on A10G2.44k🕵️♂️CLIP Interrogator
Note CLIP Interrogator is the reverted process, and let you retrieve the prompt that would have been use to generate the same kind of image than your input image
- Running699🛬
Stable Diffusion v1-5
runwayml/stable-diffusion-v1-5
Text-to-Image • Updated • 3.47M • 10.8k- Runtime error525🐼
ERNIE-ViLG
- Running on A10G418🖌️🎨
Karlo
- Running on A10G426🖼️
Stable Diffusion Image Variations
Runtime error71🌖Text to Pokémon
Note This text-to-Pokémon demo was the first to show that we could train specific dataset of images and had a huge impact.
Running902🦉Diffuse The Rest
Note This at the time, was the first doodle app to ever let you draw a very simple image, and diffuse an entire image according to your input drawing
CompVis/stable-diffusion-v1-4
Text-to-Image • Updated • 1.23M • 6.29k- Running on T4510👁
Latent Diffusion
Running131🥑📚🥑Wordalle
Note A game, based on Wordle, where you had to guess what was the prompt used to generate a 9 images grid with DALL-E
Running5.44k🥑DALL·E mini
Note The GOAT
dalle-mini/dalle-mini
Text-to-Image • Updated • 230 • 341