Same 112 film photos, two LoRAs: Flux 3 vs Krea 2 head-to-head on fal
adamho · x · 2026-10-29
Photographer @clairdlne trained Flux 3 and Krea 2 LoRAs on fal using the same set of 112 film photos she shot on an Olympus mju i (Fujifilm, Ultramax, Kodak Gold), then generated with identical prompts on fal agent.
The comparison images show the same night-time gas-station thunderstorm scene: both models produce strong film-grain, cinematic looks, but differ in lighting and human-motion details — a rare same-data, same-prompt side-by-side of photoreal LoRAs.
More from Multimodal
- Generating pop-art Halloween portraits with Flora and a vibe board — round · 2026-10-29
- Generating K-Pop music videos with a Claude Music Video skill, no MCP needed — AIandDesign · 2026-10-29
- Granary-v2 open speech model expands to 48 languages with open data and pipeline — rdesh26 · 2026-10-29
- ciguleva shares surreal AI artwork "Under the Hood of the Universe" — ciguleva · 2026-10-29
- ComfyUI Halloween workflow turns any image into a carved pumpkin video — PurzBeats · 2026-10-29
- NVIDIA FastGen ships major update: FLUX.2, LTX-2.5, Cosmos 3 plus four new acceleration methods — ArashVahdat · 2026-10-29