Stable Diffusion Image Generation
![[R logo]](../../../doc/html/Rlogo.svg)
![[Up]](../../../doc/html/left.jpg)
![[Top]](../../../doc/html/up.jpg)
Documentation for package ‘sd2R’ version 0.2.1
Help Pages
| LORA_APPLY_MODE | LoRA apply modes |
| PREDICTION | Prediction types |
| PREVIEW | Preview decode modes |
| RNG_TYPE | RNG types |
| SAMPLE_METHOD | Sampling methods |
| SCHEDULER | Schedulers |
| sd_api_start | Start sd2R REST API server |
| sd_api_stop | Stop sd2R REST API server |
| sd_app | Launch sd2R Shiny GUI |
| SD_CACHE_MODE | Cache modes |
| sd_cache_params | Create cache configuration for step caching |
| sd_convert | Convert model to different quantization format |
| sd_ctx | Create a Stable Diffusion context |
| sd_decode_latent | Decode a latent into a pixel image (low-level VAE decode) |
| sd_default_params | Default generation parameters |
| sd_denoise_step | Run a single denoise step (low-level) |
| sd_destroy_context | Release a stable diffusion context and free its VRAM |
| sd_download_model | Download a Stable Diffusion model from Kaggle Models |
| sd_encode_image | Encode an image into a latent (low-level VAE encode) |
| sd_encode_text | Encode a text prompt into conditioning (low-level) |
| sd_generate | Generate images (unified entry point) |
| sd_generate_multiref | Generate an image conditioned on multiple reference images |
| sd_generate_multi_gpu | Parallel generation across multiple GPUs |
| sd_image_to_array | Convert SD image to R numeric array |
| sd_img2img | Generate images with img2img |
| sd_inverse_noise_scale | Undo final-step latent scaling (low-level) |
| sd_list_models | List registered models |
| sd_load_image | Load image from file as SD image |
| sd_load_mask | Load a mask from a PNG file as a 1-channel SD image |
| sd_load_model | Load a registered model |
| sd_load_pipeline | Load pipeline from JSON |
| sd_node | Create a pipeline node |
| sd_noise_scale | Scale noise into the starting latent (low-level) |
| sd_pipeline | Create a pipeline from nodes |
| sd_preview_start | Enable live generation previews |
| sd_preview_stop | Disable live generation previews |
| sd_profile_get | Get raw profile events |
| sd_profile_start | Start profiling |
| sd_profile_stop | Stop profiling |
| sd_profile_summary | Build a profile summary from raw events |
| sd_read_preview | Read the current preview frame |
| sd_register_model | Register a model in the sd2R model registry |
| sd_remove_model | Remove a model from the registry |
| sd_run_pipeline | Run a pipeline |
| sd_sample | Run the sampling loop (low-level) |
| sd_sampler_begin | Open / close a step-wise sampling window (low-level) |
| sd_sampler_end | Open / close a step-wise sampling window (low-level) |
| sd_sampler_sigmas | Sigma schedule for a sampler (low-level) |
| sd_sample_stepwise | Run the sampling loop step-by-step in R (low-level) |
| sd_save_image | Save SD image to PNG file |
| sd_save_pipeline | Save pipeline to JSON |
| sd_scan_models | Scan a directory for models and register them |
| sd_supports_ref_images | Does the loaded model support reference images? |
| sd_system_info | Get system information |
| sd_txt2img | Generate images from text prompt |
| sd_txt2img_highres | High-resolution image generation via patch-based pipeline |
| sd_txt2img_tiled | Tiled diffusion sampling (MultiDiffusion) |
| SD_TYPE | Weight types (ggml quantization types) |
| sd_unload_all | Unload all models from memory |
| sd_unload_model | Unload a model from memory |
| sd_upscale_image | Upscale an image using ESRGAN |
| sd_vulkan_device_count | Get number of Vulkan GPU devices |