Diffusers documentation

🧨 Diffusers

You are viewing v0.16.0 version. A newer version v0.31.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started



🧨 Diffusers

πŸ€— DiffusersλŠ” μ‚¬μ „ν•™μŠ΅λœ λΉ„μ „ 및 μ˜€λ””μ˜€ ν™•μ‚° λͺ¨λΈμ„ μ œκ³΅ν•˜κ³ , μΆ”λ‘  및 ν•™μŠ΅μ„ μœ„ν•œ λͺ¨λ“ˆμ‹ 도ꡬ μƒμž 역할을 ν•©λ‹ˆλ‹€.

보닀 μ •ν™•ν•˜κ²Œ, πŸ€— DiffusersλŠ” λ‹€μŒμ„ μ œκ³΅ν•©λ‹ˆλ‹€:

  • 단 λͺ‡ μ€„μ˜ μ½”λ“œλ‘œ 좔둠을 μ‹€ν–‰ν•  수 μžˆλŠ” μ΅œμ‹  ν™•μ‚° νŒŒμ΄ν”„λΌμΈμ„ μ œκ³΅ν•©λ‹ˆλ‹€. (Using Diffusersλ₯Ό μ‚΄νŽ΄λ³΄μ„Έμš”) μ§€μ›λ˜λŠ” λͺ¨λ“  νŒŒμ΄ν”„λΌμΈκ³Ό ν•΄λ‹Ή 논문에 λŒ€ν•œ κ°œμš”λ₯Ό 보렀면 Pipelines을 μ‚΄νŽ΄λ³΄μ„Έμš”.
  • μΆ”λ‘ μ—μ„œ 속도 vs ν’ˆμ§ˆμ˜ μ ˆμΆ©μ„ μœ„ν•΄ μƒν˜Έκ΅ν™˜μ μœΌλ‘œ μ‚¬μš©ν•  수 μžˆλŠ” λ‹€μ–‘ν•œ λ…Έμ΄μ¦ˆ μŠ€μΌ€μ€„λŸ¬λ₯Ό μ œκ³΅ν•©λ‹ˆλ‹€. μžμ„Έν•œ λ‚΄μš©μ€ Schedulersλ₯Ό μ°Έκ³ ν•˜μ„Έμš”.
  • UNetκ³Ό 같은 μ—¬λŸ¬ μœ ν˜•μ˜ λͺ¨λΈμ„ end-to-end ν™•μ‚° μ‹œμŠ€ν…œμ˜ ꡬ성 μš”μ†Œλ‘œ μ‚¬μš©ν•  수 μžˆμŠ΅λ‹ˆλ‹€. μžμ„Έν•œ λ‚΄μš©μ€ Models을 μ°Έκ³ ν•˜μ„Έμš”.
  • κ°€μž₯ μΈκΈ°μžˆλŠ” ν™•μ‚° λͺ¨λΈ ν…ŒμŠ€ν¬λ₯Ό ν•™μŠ΅ν•˜λŠ” 방법을 λ³΄μ—¬μ£ΌλŠ” μ˜ˆμ œλ“€μ„ μ œκ³΅ν•©λ‹ˆλ‹€. μžμ„Έν•œ λ‚΄μš©μ€ Trainingλ₯Ό μ°Έκ³ ν•˜μ„Έμš”.

🧨 Diffusers νŒŒμ΄ν”„λΌμΈ

λ‹€μŒ ν‘œμ—λŠ” κ³΅μ‹œμ μœΌλ‘œ μ§€μ›λ˜λŠ” λͺ¨λ“  νŒŒμ΄ν”„λΌμΈ, κ΄€λ ¨ λ…Όλ¬Έ, 직접 μ‚¬μš©ν•΄ λ³Ό 수 μžˆλŠ” Colab λ…ΈνŠΈλΆ(μ‚¬μš© κ°€λŠ₯ν•œ 경우)이 μš”μ•½λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€.

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

μ°Έκ³ : νŒŒμ΄ν”„λΌμΈμ€ ν•΄λ‹Ή λ¬Έμ„œμ— μ„€λͺ…λœ λŒ€λ‘œ ν™•μ‚° μ‹œμŠ€ν…œμ„ μ‚¬μš©ν•œ 방법에 λŒ€ν•œ κ°„λ‹¨ν•œ μ˜ˆμž…λ‹ˆλ‹€.