Model reference · open weights
Prompt-Refine is an open-weight language model from HiDream-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Prompt Refine model for HiDream-O1-Image-Dev-2604. Finetuned from gemma-4-31b-it
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | HiDream-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 31.3B |
| Variants | 1 |
| Runs with | transformers |
| Based on | google/gemma-4-31B-it |
| Released | 2026-05-13 |
| Popularity | 389 downloads / month |
| Likes | 18 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Prompt-Refine | 31.3B | BF16 | ~71.9 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys prompt-refine for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (prompt-refine below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"prompt-refine","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗