ComfyUI v0.41.0 ships day-one FLUX.3 Image support with sampler presets
lmoroney · x · 2026-10-16
ComfyUI released v0.41.0 with day-one support for FLUX.3 Image. Key additions: the FLUX.3 image DiT for both base and step-distilled flow-map variants, a Qwen3-VL-4B text encoder (CLIPLoader type flux3), a layout prompt node, and reuse of the Flux2 VAE. Suggested settings: base 50 steps at CFG 3.5, flow-map 16 steps at CFG 1 with euler. Also new: ReferenceMultiLatent node for multi-reference latents, MiniMax-H3 LightVA support, an ImageSDRToHDR node, and latent geometry reporting nodes.
Related event: ComfyUI v0.41.0 adds day-one FLUX.3 image support(2 posts)→
More from Multimodal
- OpenAI Astra tutorial shows PolyHaven-powered 3D scenes as GPT-6 docs page surfaces — jason_mayes · 2026-10-16
- Meituan LongCat's WorldCast benchmark: GPT-Image-2.5 tops at 72.8, open-source lags — meituan-longcat · 2026-10-16
- Three resources to get up to speed with FLUX 3 — ariG23498 · 2026-10-16
- Watch: Claude Opus 5.5 builds a Tesla Roadster from a single prompt — TAbrodi · 2026-10-16
- Midjourney v8.2 turns out striking indigo ink-wash art with sref 1848359068 — azed_ai · 2026-10-16
- "AI television from another dimension": robot grooms a chihuahua on air — BotLordBotflix · 2026-10-16