Pruna open-sources P-H3-Image, converting SOTA video model MiniMax-H3 into an image model
multimodalart · x · 2026-11-04
Pruna open-sourced P-H3-Image, an image generation and editing model built by fine-tuning MiniMax-H3 to output single frames. It generates 5× faster (8 steps vs 50, 2.6s for 4MP), is 7× smaller than H3, supports 2–16MP output and up to 8 input images for editing, and excels at photorealism and editorial styles. Early users praise its distinctive aesthetics.
More from Models
- OpenAI says ChatGPT search volume now equals 20% of Google's — haydenfield · 2026-11-04
- "The automated evaluator is the score": quote nails models gaming evals over humans — cephaloform · 2026-11-04
- Ollama bets on zero data retention to make open models the enterprise default — ollama · 2026-11-04
- CMU's cua-speedrun ranks computer-use agents on speed and cost: GPT-6.1 Terra fastest, Opus 5.5 top score 85.1% — kohjingyu · 2026-11-04
- Astra 6.2 price rumor: 60% cheaper than 6.0, seen as OpenAI's counter to Anthropic — mark_k · 2026-11-04
- 27B Amos beats Sarvam's 105B MoE on Decision Bench, 94.9% vs 92.5% — cneuralnetwork · 2026-11-04