saba99 / Text2MotionImages

Text To Motion Images With Diffusion Models

Text2 Motion Images(Video)

Click on each gif to see the full motion

Video/Prompt(word base)	Video/Prompt(word base)	Video/Prompt(word base)	Video/Prompt(word base)
girl,-offshoulder,-light-smile,-shiny-skin-best-quality,-masterpiece,-photorealistic	cut-tusuncub-walking-in-the-snow,-blurry,-looking-at-viewer	character-design,-cyberpunk-tusun-kitten-wearing-astronaut-suit,-sci-fic,-realistic	best-quality,-masterpiece,-photorealistic,-1girl,-light-smile,-shirt-with-collars
Video/Prompt(Sentence base)	Video/Prompt(Sentence base)	Video/Prompt(Sentence base)	Video/Prompt(Sentence base)
The_astronaut_dances_in_futuristic..	A_daring_man_performing_gravity-defying	A_daring_man_is_scaling_a_treacherous..	A_mighty_elephant_marches_steadily.

🎆🎆Models..

• Please download the MotionLoRA models (74 MB per model, available at Google Drive / HuggingFace and save them to the models/MotionLoRA folder. Example:

python -m scripts.animate --config configs/prompts/v2/5-RealisticVision-MotionLoRA.yaml

mm_sd_v15_v2.ckpt was trained on larger resolution & batch size, and gains noticeable quality improvements. Check it out at Google Drive and use it with configs/inference/inference-v2.yaml. Example:

python -m scripts.animate --config configs/prompts/v2/5-RealisticVision.yaml

🖨🖨Run

python app.py

By default, the demo will run at localhost:7860.