{"slug": "stable-diffusion-cpp", "name": "stable-diffusion.cpp", "category": "media", "category_name": "Media and creative", "description": "", "recommenders": 4, "commenters": 7, "warners": 1, "score": 3.236, "rising": 2.67, "first": "2025-12-06", "latest": "2026-10-13", "why": "It is for people that know command line shells like bash or Powershell.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 0, "warn": 1}, "spark": [0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 2, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "It is for people that know command line shells like bash or Powershell.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/leejet/stable-diffusion.cpp", "official_url": "https://github.com/leejet/stable-diffusion.cpp", "pricing": "", "aliases": ["stable-diffusion.cpp"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 796439120, "item_id": 49777445, "url": "https://news.ycombinator.com/item?id=49777445", "by": "peri-cl", "date": "2026-09-20", "stance": "recommend", "quote": "It works out of the box.", "excerpt": "I've set it up on my local machine just now, as my first local image diffuser. I can confirm it's very easy. I tried stable-diffusion.cpp, following its compile guide here[0], and its Qwen Image-2.1 specific instructions here[1]. It works out of the box. I made a test pelican[2]. It took 3 minutes on a CPU. [0] https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/build.md [1] https://github.com/leejet/stab", "context": "", "use_case": "", "switched_from": "", "story": "Qwen Image 2.1"}, {"id": 796430512, "item_id": 49776907, "url": "https://news.ycombinator.com/item?id=49776907", "by": "nkhgfugjk", "date": "2026-09-20", "stance": "recommend", "quote": "it already has day-0 qwen image 2.1 support!", "excerpt": "I am using sd.cpp, which is the cousin of llama.cpp: https://github.com/leejet/stable-diffusion.cpp it already has day-0 qwen image 2.1 support!", "context": "", "use_case": "Local image generation", "switched_from": "", "story": "Qwen Image 2.1"}, {"id": 788386288, "item_id": 49274143, "url": "https://news.ycombinator.com/item?id=49274143", "by": "qclibre22", "date": "2026-08-12", "stance": "recommend", "quote": "It is for people that know command line shells like bash or Powershell.", "excerpt": "There's also sdcpp ( https://github.com/leejet/stable-diffusion.cpp ) . It is for people that know command line shells like bash or Powershell. SDCPP is like llama.cpp but it is for using text to image AI models. Not everyone likes the node/graph programming interface in Comfy or a Webpage interface. Some people need these GUI/web interfaces and get lost and frustrated in shell scripting.", "context": "", "use_case": "Text-to-image from CLI", "switched_from": "", "story": "Automatic1111 for Apple metal, 40% speed up sd1.5"}, {"id": 746750208, "item_id": 46671888, "url": "https://news.ycombinator.com/item?id=46671888", "by": "badsectoracula", "date": "2026-01-18", "stance": "recommend", "quote": "FWIW stable-diffusion.cpp[0] (which implements a lot more than just stable diffusion", "excerpt": "FWIW stable-diffusion.cpp[0] (which implements a lot more than just stable diffusion, despite the name) is already a MIT licensed C++ library. [0] https://github.com/leejet/stable-diffusion.cpp/", "context": "", "use_case": "", "switched_from": "", "story": "Flux 2 Klein pure C inference"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 801172288, "item_id": 50073268, "url": "https://news.ycombinator.com/item?id=50073268", "by": "netdur", "date": "2026-10-13", "stance": "warn", "quote": "the sd.cpp take too much time on my laptop to generate image", "excerpt": "I did, the sd.cpp take too much time on my laptop to generate image, the issue is known and it did not seem like it gonna be resolved, so I build my own, and that's why https://github.com/netdur/qwen-image-cplus", "context": "", "use_case": "", "switched_from": "", "story": "Janas: Run LLMs larger than RAM by streaming experts from SSD"}]}], "who": [], "tags": [], "use_cases": ["local image generation", "text-to-image from cli"], "compared": [{"slug": "comfyui", "name": "ComfyUI", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "qwen-image", "name": "Qwen-Image", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49775499", "title": "Qwen Image 2.1", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50063717", "title": "Janas: Run LLMs larger than RAM by streaming experts from SSD", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49272282", "title": "Automatic1111 for Apple metal, 40% speed up sd1.5", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46670279", "title": "Flux 2 Klein pure C inference", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46444454", "title": "How to Run Qwen-Image-2512 Locally in ComfyUI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46095817", "title": "Z-Image: Powerful and highly efficient image generation model with 6B parameters", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"neutral": 2}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {"recommend": 2}, "2026-10": {"warn": 1}}, "quotes": [{"id": 801172288, "item_id": 50073268, "url": "https://news.ycombinator.com/item?id=50073268", "by": "netdur", "date": "2026-10-13", "stance": "warn", "quote": "the sd.cpp take too much time on my laptop to generate image", "excerpt": "I did, the sd.cpp take too much time on my laptop to generate image, the issue is known and it did not seem like it gonna be resolved, so I build my own, and that's why https://github.com/netdur/qwen-image-cplus", "context": "", "use_case": "", "switched_from": "", "story": "Janas: Run LLMs larger than RAM by streaming experts from SSD"}, {"id": 796439120, "item_id": 49777445, "url": "https://news.ycombinator.com/item?id=49777445", "by": "peri-cl", "date": "2026-09-20", "stance": "recommend", "quote": "It works out of the box.", "excerpt": "I've set it up on my local machine just now, as my first local image diffuser. I can confirm it's very easy. I tried stable-diffusion.cpp, following its compile guide here[0], and its Qwen Image-2.1 specific instructions here[1]. It works out of the box. I made a test pelican[2]. It took 3 minutes on a CPU. [0] https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/build.md [1] https://github.com/leejet/stab", "context": "", "use_case": "", "switched_from": "", "story": "Qwen Image 2.1"}, {"id": 796430512, "item_id": 49776907, "url": "https://news.ycombinator.com/item?id=49776907", "by": "nkhgfugjk", "date": "2026-09-20", "stance": "recommend", "quote": "it already has day-0 qwen image 2.1 support!", "excerpt": "I am using sd.cpp, which is the cousin of llama.cpp: https://github.com/leejet/stable-diffusion.cpp it already has day-0 qwen image 2.1 support!", "context": "", "use_case": "Local image generation", "switched_from": "", "story": "Qwen Image 2.1"}, {"id": 788386288, "item_id": 49274143, "url": "https://news.ycombinator.com/item?id=49274143", "by": "qclibre22", "date": "2026-08-12", "stance": "recommend", "quote": "It is for people that know command line shells like bash or Powershell.", "excerpt": "There's also sdcpp ( https://github.com/leejet/stable-diffusion.cpp ) . It is for people that know command line shells like bash or Powershell. SDCPP is like llama.cpp but it is for using text to image AI models. Not everyone likes the node/graph programming interface in Comfy or a Webpage interface. Some people need these GUI/web interfaces and get lost and frustrated in shell scripting.", "context": "", "use_case": "Text-to-image from CLI", "switched_from": "", "story": "Automatic1111 for Apple metal, 40% speed up sd1.5"}, {"id": 746750208, "item_id": 46671888, "url": "https://news.ycombinator.com/item?id=46671888", "by": "badsectoracula", "date": "2026-01-18", "stance": "recommend", "quote": "FWIW stable-diffusion.cpp[0] (which implements a lot more than just stable diffusion", "excerpt": "FWIW stable-diffusion.cpp[0] (which implements a lot more than just stable diffusion, despite the name) is already a MIT licensed C++ library. [0] https://github.com/leejet/stable-diffusion.cpp/", "context": "", "use_case": "", "switched_from": "", "story": "Flux 2 Klein pure C inference"}, {"id": 743111954, "item_id": 46444497, "url": "https://news.ycombinator.com/item?id=46444497", "by": "homarp", "date": "2025-12-31", "stance": "neutral", "quote": "Or you can try", "excerpt": "Qwen released their updated Image model: https://huggingface.co/Qwen/Qwen-Image-2512 One way to run it is with ComfyUI https://www.comfy.org/ Or you can try https://github.com/leejet/stable-diffusion.cpp", "context": "", "use_case": "", "switched_from": "", "story": "How to Run Qwen-Image-2512 Locally in ComfyUI"}, {"id": 738839648, "item_id": 46177478, "url": "https://news.ycombinator.com/item?id=46177478", "by": "opensandwich", "date": "2025-12-06", "stance": "neutral", "quote": "though apparently it already exists", "excerpt": "(Not tested) though apparently it already exists: https://github.com/leejet/stable-diffusion.cpp/wiki/How-to-Use-Z%E2%80%90Image-on-a-GPU-with-Only-4GB-VRAM", "context": "", "use_case": "Local image generation", "switched_from": "", "story": "Z-Image: Powerful and highly efficient image generation model with 6B parameters"}]}