Open-source · Images · 4 of 22 tools · updated Oct 17, 2026
Open-source AI tools to generate images from text
ComfyUI leads the open-source options to generate images from text at 97/100, with 137,960 GitHub stars. 4 of the 22 tools tracked for this job publish their source, so you can read it, fork it or self-host it. It is also the top-ranked tool for this job overall, open-source or not.
Same evidence score as the ranking — GitHub stars, Hacker News mentions, release activity, free access — recomputed nightly, never sold. See all 22 tools to generate images from text.
Top 3
evidence / 100
+ Gets day-one support for new open models (Flux, Wan, Hunyuan) and lets you wire up any pipeline you can imagine.
− The node graph has a steep learning curve and shared workflows frequently break on missing custom nodes.
+ Produces good SDXL results with zero tuning, making it the easiest local generator to start with.
− In maintenance mode and tied to SDXL, so it does not support newer models like Flux.
+ Best prompt adherence and hand/text rendering of any open-weight image model, with Kontext adding instruction-based editing.
− The dev weights are non-commercial, and the 12B model needs a 16GB+ GPU to run comfortably.
All 4, side by side
| Tool | Score | Stars | Source | Days idle | Platforms |
|---|---|---|---|---|---|
| ComfyUI | 97 | 137,960 | comfyanonymous/ComfyUI | 0 | windows, mac, linux |
| Fooocus | 75 | 53,551 | lllyasviel/Fooocus | 319 | windows, linux |
| FLUX (Black Forest Labs) | 72 | 26,021 | black-forest-labs/flux | 442 | api, linux, web |
 Stable Diffusion WebUI (AUTOMATIC1111) | 64 | 165,071 | AUTOMATIC1111/stable-diffusion-webui | 228 | windows, mac, linux |
Open source here means the tool's own source is public, not that a vendor published an SDK. Self-hosting cost is yours.
Head to head: ComfyUI vs Fooocus ComfyUI vs FLUX (Black Forest Labs) Fooocus vs FLUX (Black Forest Labs)