The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Commits on master
Fix linear_input_act to respect _full_precision_mm fallback (#16285)
a20738f Jialong(Bruce) Li committed 2 months ago
Don't add noise to the alpha channel in the Add Noise to Image node (#15626)
7ba217d Christian Byrne committed 2 months ago
[Partner Nodes] feat(client): consume estimated-duration headers for progress display (#16152)
9113c08 Alexander Piskun committed 2 months ago
[Partner Nodes] feat(Bria): add new image edit nodes and the Video Eraser node (#16264)
c75d8c9 Alexander Piskun committed 2 months ago
[Partner Nodes] feat(OpenRouter): add auto aspect ratio to the MAI image node (#16229)
5774ab9 Alexander Piskun committed 2 months ago
[Partner Nodes] feat(Tripo): migrate to the v3 API, add the Smart Segment node and retire the dead widgets (#16201)
6eba895 Alexander Piskun committed 2 months ago
Update instructions for manual install on windows AMD. (#16217)
a7b1d39 comfyanonymous committed 2 months ago
[Partner Nodes] feat(Gemini-LLM): Add Gemini 3.8 Flash to the Gemini text node (#16195)
7ea14e5 Alexander Piskun committed 2 months ago
[Partner Noes] feat(OpenRouter): add Microsoft `mai-image-2.6` models (#16188)
4989cdd Alexander Piskun committed 2 months ago
Add new model blueprints and reorganize subgraph categories (#14785)
54e03f5 Daxiong (Lin) committed 2 months ago
Report the file saved by Save 3D (Advanced) as a standard 3d output item (#16171)
3074d0e Terry Jia committed 2 months ago
chores: Update tooltips of 3D nodes (CORE-323) (#16179)
02dfb63 Alexis Rolland committed 2 months ago
[Partner Nodes] feat(OpenAI): add GPT Image 2.5 Flare and Sunburst models (#16190)
be47aa2 Alexander Piskun committed 2 months ago
Only lock repo PRs after merging if they contain a CLA signature. (#16191)
672ba9e comfyanonymous committed 2 months ago
Add LTXVAddLatentGuide for pinning a pre-encoded latent as a guide (#16176)
0d0b6b5 Alex Artyomov committed 2 months ago
Cleaner way of enabling quantized mm on text gen but not on text enc. (#16189)
249c5a3 comfyanonymous committed 2 months ago