Diffusers documentation

๐Ÿงจ Diffusers

You are viewing v0.20.0 version. A newer version v0.30.3 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started



๐Ÿงจ Diffusers

๐Ÿค— Diffusers๋Š” ์‚ฌ์ „ํ•™์Šต๋œ ๋น„์ „ ๋ฐ ์˜ค๋””์˜ค ํ™•์‚ฐ ๋ชจ๋ธ์„ ์ œ๊ณตํ•˜๊ณ , ์ถ”๋ก  ๋ฐ ํ•™์Šต์„ ์œ„ํ•œ ๋ชจ๋“ˆ์‹ ๋„๊ตฌ ์ƒ์ž ์—ญํ• ์„ ํ•ฉ๋‹ˆ๋‹ค.

๋ณด๋‹ค ์ •ํ™•ํ•˜๊ฒŒ, ๐Ÿค— Diffusers๋Š” ๋‹ค์Œ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค:

  • ๋‹จ ๋ช‡ ์ค„์˜ ์ฝ”๋“œ๋กœ ์ถ”๋ก ์„ ์‹คํ–‰ํ•  ์ˆ˜ ์žˆ๋Š” ์ตœ์‹  ํ™•์‚ฐ ํŒŒ์ดํ”„๋ผ์ธ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. (Using Diffusers๋ฅผ ์‚ดํŽด๋ณด์„ธ์š”) ์ง€์›๋˜๋Š” ๋ชจ๋“  ํŒŒ์ดํ”„๋ผ์ธ๊ณผ ํ•ด๋‹น ๋…ผ๋ฌธ์— ๋Œ€ํ•œ ๊ฐœ์š”๋ฅผ ๋ณด๋ ค๋ฉด Pipelines์„ ์‚ดํŽด๋ณด์„ธ์š”.
  • ์ถ”๋ก ์—์„œ ์†๋„ vs ํ’ˆ์งˆ์˜ ์ ˆ์ถฉ์„ ์œ„ํ•ด ์ƒํ˜ธ๊ตํ™˜์ ์œผ๋กœ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋Š” ๋‹ค์–‘ํ•œ ๋…ธ์ด์ฆˆ ์Šค์ผ€์ค„๋Ÿฌ๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์ž์„ธํ•œ ๋‚ด์šฉ์€ Schedulers๋ฅผ ์ฐธ๊ณ ํ•˜์„ธ์š”.
  • UNet๊ณผ ๊ฐ™์€ ์—ฌ๋Ÿฌ ์œ ํ˜•์˜ ๋ชจ๋ธ์„ end-to-end ํ™•์‚ฐ ์‹œ์Šคํ…œ์˜ ๊ตฌ์„ฑ ์š”์†Œ๋กœ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์ž์„ธํ•œ ๋‚ด์šฉ์€ Models์„ ์ฐธ๊ณ ํ•˜์„ธ์š”.
  • ๊ฐ€์žฅ ์ธ๊ธฐ์žˆ๋Š” ํ™•์‚ฐ ๋ชจ๋ธ ํ…Œ์Šคํฌ๋ฅผ ํ•™์Šตํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ๋ณด์—ฌ์ฃผ๋Š” ์˜ˆ์ œ๋“ค์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์ž์„ธํ•œ ๋‚ด์šฉ์€ Training๋ฅผ ์ฐธ๊ณ ํ•˜์„ธ์š”.

๐Ÿงจ Diffusers ํŒŒ์ดํ”„๋ผ์ธ

๋‹ค์Œ ํ‘œ์—๋Š” ๊ณต์‹œ์ ์œผ๋กœ ์ง€์›๋˜๋Š” ๋ชจ๋“  ํŒŒ์ดํ”„๋ผ์ธ, ๊ด€๋ จ ๋…ผ๋ฌธ, ์ง์ ‘ ์‚ฌ์šฉํ•ด ๋ณผ ์ˆ˜ ์žˆ๋Š” Colab ๋…ธํŠธ๋ถ(์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ๊ฒฝ์šฐ)์ด ์š”์•ฝ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.

Pipeline Paper Tasks Colab
alt_diffusion AltDiffusion Image-to-Image Text-Guided Generation
audio_diffusion Audio Diffusion Unconditional Audio Generation Open In Colab
cycle_diffusion Cycle Diffusion Image-to-Image Text-Guided Generation
dance_diffusion Dance Diffusion Unconditional Audio Generation
ddpm Denoising Diffusion Probabilistic Models Unconditional Image Generation
ddim Denoising Diffusion Implicit Models Unconditional Image Generation
latent_diffusion High-Resolution Image Synthesis with Latent Diffusion Models Text-to-Image Generation
latent_diffusion High-Resolution Image Synthesis with Latent Diffusion Models Super Resolution Image-to-Image
latent_diffusion_uncond High-Resolution Image Synthesis with Latent Diffusion Models Unconditional Image Generation
paint_by_example Paint by Example: Exemplar-based Image Editing with Diffusion Models Image-Guided Image Inpainting
pndm Pseudo Numerical Methods for Diffusion Models on Manifolds Unconditional Image Generation
score_sde_ve Score-Based Generative Modeling through Stochastic Differential Equations Unconditional Image Generation
score_sde_vp Score-Based Generative Modeling through Stochastic Differential Equations Unconditional Image Generation
stable_diffusion Stable Diffusion Text-to-Image Generation Open In Colab
stable_diffusion Stable Diffusion Image-to-Image Text-Guided Generation Open In Colab
stable_diffusion Stable Diffusion Text-Guided Image Inpainting Open In Colab
stable_diffusion_2 Stable Diffusion 2 Text-to-Image Generation
stable_diffusion_2 Stable Diffusion 2 Text-Guided Image Inpainting
stable_diffusion_2 Stable Diffusion 2 Text-Guided Super Resolution Image-to-Image
stable_diffusion_safe Safe Stable Diffusion Text-Guided Generation Open In Colab
stochastic_karras_ve Elucidating the Design Space of Diffusion-Based Generative Models Unconditional Image Generation
unclip Hierarchical Text-Conditional Image Generation with CLIP Latents Text-to-Image Generation
versatile_diffusion Versatile Diffusion: Text, Images and Variations All in One Diffusion Model Text-to-Image Generation
versatile_diffusion Versatile Diffusion: Text, Images and Variations All in One Diffusion Model Image Variations Generation
versatile_diffusion Versatile Diffusion: Text, Images and Variations All in One Diffusion Model Dual Image and Text Guided Generation
vq_diffusion Vector Quantized Diffusion Model for Text-to-Image Synthesis Text-to-Image Generation

์ฐธ๊ณ : ํŒŒ์ดํ”„๋ผ์ธ์€ ํ•ด๋‹น ๋ฌธ์„œ์— ์„ค๋ช…๋œ ๋Œ€๋กœ ํ™•์‚ฐ ์‹œ์Šคํ…œ์„ ์‚ฌ์šฉํ•œ ๋ฐฉ๋ฒ•์— ๋Œ€ํ•œ ๊ฐ„๋‹จํ•œ ์˜ˆ์ž…๋‹ˆ๋‹ค.