Text to image

Models that generate images from text prompts

stability-ai / stable-diffusion

A latent text-to-image diffusion model capable of generating photo-realistic images given any text input

99.2M runs

pixray / text2image

Uses pixray to generate an image from text prompt

1.4M runs

cjwbw / waifu-diffusion

Stable Diffusion on Danbooru images

1.1M runs

kuprel / min-dalle

Fast, minimal port of DALL·E Mini to PyTorch

499.7K runs

laion-ai / erlich

Generate a logo using text.

316.3K runs

deforum / deforum_​stable_​diffusion

Animating prompts with stable diffusion

178.1K runs

mehdidc / feed_​forward_​vqgan_​clip

Feed forward VQGAN-CLIP model

128.1K runs

laion-ai / ongo

Generate a painting using text.

119K runs

cjwbw / stable-diffusion-high-resolution

Detailed, higher-resolution images from Stable Diffusion

65.3K runs

nightmareai / disco-diffusion

Generate images using a variety of techniques - Powered by Discoart

62.8K runs

borisdayma / dalle-mini

Generate images from a text prompt

56.8K runs

jack000 / glid-3-xl

A 1.4B parameter text2im model from CompVis, finetuned on CLIP text embeds and curated data.

45.1K runs

afiaka87 / retrieval-augmented-diffusion

Generate 768px images from text using CompVis `retrieval-augmented-diffusion`

37.1K runs

cjwbw / stable-diffusion-v1-5

stable-diffusion with v1-5 checkpoint

34K runs

nightmareai / cogvideo

Text-to-video generation

30.2K runs

meta / ic_​gan

Instance-Conditioned GAN

26.4K runs

cjwbw / vq-diffusion

VQ-Diffusion for Text-to-Image Synthesis

20.6K runs

xl-sr / projected_​gan

Generate Pokemons with Projected GAN

9.7K runs

afiaka87 / laionide-v4

GLIDE-text2im w/ humans and experimental style prompts.

9.1K runs

nightmareai / majesty-diffusion

Generate images from text using CLIP guided latent diffusion

7.9K runs

nitrosocke / archer-diffusion

Archer on Stable Diffusion via Dreambooth

7.2K runs

nightmareai / k-diffusion

CLIP Guided latent k-diffusion

6.6K runs

ouhenio / stylegan3-clip

stylegan3 + clip

6.4K runs

cjwbw / clip-guided-diffusion-pokemon

Generates pokemon sprites from prompt

4.7K runs

kvfrans / clipdraw

Synthesize drawings to match a text prompt

4.4K runs

ekgren / structureddreaming

Styledreams -- CLIP x Stylegan2

3.9K runs

nicholascelestin / glid-3

Generate images quickly with GLID-3 (non-xl)

3.9K runs

cjwbw / latent-diffusion-text2img

text-to-image with latent diffusion

3.8K runs

laion-ai / puck

Generate retro videogame art using text.

3.5K runs

gnobitab / fusedream

Training-Free Text-to-Image Generation

2.4K runs

cjwbw / sd-textual-inversion-ugly-sonic

stable-diffusion-textual-inversion fine-tuned with ugly sonic

1.9K runs

pschaldenbrand / style-clip-draw

Styled text-to-drawing synthesis method.

1.7K runs

cjwbw / mindall-e

text-to-image generation

1.6K runs

huiyegit / t2i_​cl

Text-to-image synthesis using contrastive learning

1.2K runs

cjwbw / clip-gen

Language-Free Training of a Text-to-Image Generator with CLIP

805 runs

cjwbw / compositional-vsual-generation-with-composable-diffusion-models-pytorch

Composable Diffusion

763 runs

andreasjansson / monkey-island-rdm

Monkey Island database for Retrieval-augmented Diffusion model

600 runs

vivalapanda / waifu-diffusion

7 runs