by Pruna AIImageNew
P-H3-Image LoRA
P-H3-Image stills and edits with up to three H3 LoRAs
- Up to 4K
- Up to 9 reference images
- 15 aspect ratios
- Loads your own LoRA
From 42 credits per image≈ $0.042· Create Image
What it's like to use
P-H3-Image LoRA is Pruna AI's P-H3-Image with up to three MiniMax H3 LoRA files loaded, each with its own strength from 0 to 4. It makes stills from a written scene or edits using up to nine pictures, in five sizes up to 4K.
Good for
- Applying a character or house style trained as an H3 LoRA to stills
- Comparing a LoRA on and off with the same seed
- Carrying a trained style onto your own photo
What P-H3-Image LoRA can do
How to prompt P-H3-Image LoRA
- Paste the link that downloads the .safetensors file itself, such as a Hugging Face resolve/main link. A LoRA the model can't load is skipped and the image is still charged.
- Use LoRAs trained for MiniMax H3, and start the prompt with the LoRA's trigger words.
- Keep the seed fixed and run once with the LoRA strength at 0 to see what the LoRA changes.
Settings worth knowing
resolution1K · 1.5K · 2K · 3K · 4K- Choose an available output size.
aspect_ratio1:1 · 16:9 · 9:16 · 4:3 +11- The shape of the frame: wide, square or tall.
image_urls≤ 9- Photos to edit or combine. Say in the prompt what each one adds.
seed0–2147483647- Use the same seed and settings for more controlled comparisons.
loras≤ 3- Add LoRA weights compatible with this model to guide its style or character.
output_formatjpeg · png · webp- File type of the result.
How it compares
Without LoRAs, P-H3-Image does the same text to image and editing for less per image.
Good to know
Up to three LoRAs per run. A LoRA that can't be loaded is skipped and still charged.
Questions about P-H3-Image LoRA
How much does P-H3-Image LoRA cost?
On PopNow, the cheapest run of P-H3-Image LoRA costs 42 credits ($0.042) per image. Larger sizes cost more: 1K 42 · 1.5K 54 · 2K 66 · 3K 114 · 4K 162.
What can P-H3-Image LoRA do?
On PopNow, P-H3-Image LoRA works in these modes: Create Image and Edit Image. Pick one in the studio and add a prompt or an upload.
What sizes can P-H3-Image LoRA make?
P-H3-Image LoRA renders up to 4K in 15 aspect ratios, and edits with up to 9 reference images.
How should I write prompts for P-H3-Image LoRA?
Paste the link that downloads the .safetensors file itself, such as a Hugging Face resolve/main link. A LoRA the model can't load is skipped and the image is still charged. Use LoRAs trained for MiniMax H3, and start the prompt with the LoRA's trigger words. Keep the seed fixed and run once with the LoRA strength at 0 to see what the LoRA changes.
P-H3-Image LoRA or P-H3-Image?
Without LoRAs, P-H3-Image does the same text to image and editing for less per image.
Do I need to install anything to use P-H3-Image LoRA?
No. P-H3-Image LoRA runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.