# Is P-H3-Image SOTA?

Pending benchmarks. Announced Nov 3, 2026; no independent results yet.

As of Nov 22, 2026, P-H3-Image is pending benchmarks on isitsota: announced Nov 3, 2026, with no independent results on the boards we track yet.

Pruna AI's open-weights text-to-image and image-editing model, rebuilt from the MiniMax-H3 video model: 8 sampling steps instead of 50, no classifier-free guidance, 2 to 16 MP output and edits with up to 8 input images. Weights on Hugging Face under the MiniMax H3 Community License, for Diffusers and ComfyUI.

Canonical: https://isitsota.com/m/p-h3-image
Last updated: 2026-11-03
Tracking since: 2026-11-03

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Pruna AI |
| Announced | Nov 3, 2026 |
| API | Not yet · No hosted API stated in the launch materials |
| Open weights | Published · Hugging Face PrunaAI/P-H3-Image (Diffusers ModularPipeline, about 100 GB in bf16) and PrunaAI/P-H3-Image-Comfy (int8 and 4-bit files for ComfyUI); not gated; a Playground on Hugging Face Spaces |
| Parameters | 33.1B-parameter transformer per the card (66 GB in bf16), plus a 4B text encoder and a prompt upsampler based on Qwen3.5-9B; Pruna's blog describes the backbone as 20B after replacing H3's timestep block |
| Type | Text-to-image and image editing (1 to 8 input images); single images only, no video or audio |
| Base model | MiniMaxAI/MiniMax-H3 (a video model), fine-tuned and reworked: prompt upsampler, text encoder, diffusion schedule, transformer and decoder |
| Sampling | 8 steps (distilled from 50), no CFG or negative prompt |
| Resolution | 2 to 16 MP; the card recommends 8 MP for text-to-image and 4 or 8 MP for edits |
| Text encoder | 4B, distilled from H3's 32B encoder (9 GB vs 67 GB per the blog) |
| Prompt upsampler | Included and on by default, based on Qwen3.5-9B |
| Hardware | About 101 GB GPU memory at 8 MP in bf16 with the upsampler (83 GB without), or 80 GB with offloading; the 4-bit ComfyUI build runs in about 21 GB |
| License | MiniMax H3 Community License: excludes the EU, UK, Republic of Korea and US without a separate MiniMax license and requires "Powered by MiniMax H3"; Qwen-derived parts Apache 2.0, ComfyUI nodes MIT |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: 5x faster than MiniMax-H3 with 8 steps instead of 50: a 4 MP image in 2.6 s vs 12.4 s on one B200 (5.8 s vs 30.6 s at 8 MP).
- Lab claim: 7x smaller than H3 at its smallest (a 20 GB 4-bit download vs 143 GB), running 8 MP images in about 21 GB of VRAM.
- Lab claim: for most prompts, the 8-step model matches the 50-step original.

## Sources

- LAB: [P-H3-Image launch post (Pruna blog)](https://www.pruna.ai/blog/oss-p-h3-image-launch) (2026-11-03)
- LAB: [Pruna AI announcement on X](https://x.com/PrunaAI/status/2117663564487926043) (2026-11-03)
- REPO: [PrunaAI/P-H3-Image on Hugging Face](https://huggingface.co/PrunaAI/P-H3-Image)
- REPO: [PrunaAI/P-H3-Image-Comfy on Hugging Face](https://huggingface.co/PrunaAI/P-H3-Image-Comfy)

Tracking continues until an independent board lists it.

## Related

- Lab: [Pruna AI](https://isitsota.com/labs/pruna-ai.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/p-h3-image
