Hedra says its AMD tuning cuts Krea 3 image edits to 3.6 seconds

Hedra said it cut 2K image edits with Krea 3 to 3.6 seconds on AMD Instinct MI355X accelerators, down from about 22 seconds on the same hardware, after rebuilding its inference stack with custom ROCm kernels and lower-precision math. The San Francisco startup added Krea 3, a reference-driven image generation and editing model, to its platform on October 15th and announced the roughly sixfold speedup in a six-post thread on X. Hedra is pitching the AMD inference optimizations as part of its infrastructure offer for serving third-party models, and the speed claim remains company-reported.

Hedra says its AMD tuning cuts Krea 3 image edits to 3.6 seconds The San Francisco startup says custom ROCm kernels and lower-precision math cut a 2K edit from about 22 seconds on the same MI355X hardware. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: X https://x.com/hedra labs/status/2110763001372708992?s=46 Why it matters Hedra is pitching its infrastructure as a way to serve third-party models, with AMD inference optimizations as part of the offer. The sixfold speed claim remains company-reported. Hedra added Krea 3, a reference-driven image generation and editing model, to its platform on October 15th. In a six-post thread on X https://x.com/hedra labs/status/2110763001372708992?s=46 , the startup said it can return a 2K edit in 3.6 seconds on AMD Instinct MI355X accelerators, down from about 22 seconds on the same hardware before it rebuilt its inference stack.