Soul Standard
imageHiggsfield's first Soul model. An image from a prompt, at 720p or 1080p, with no picture to attach.
Other versions
What it supports
- Aspect ratios
- 9:16, 16:9, 4:3, 3:4, 1:1, 2:3, 3:2
- Resolutions
- 720p, 1080p
- Per request
- up to 4
- Prompt enhance
- Supported
What it costs
- 720p
- 20 credits
- 1080p
- 36 credits
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Soul Standard is Higgsfield's first Soul image model. It makes a picture from a prompt, at 720p or 1080p. It does not take a picture.
How to use it on Visxy
Write the prompt. There is no picture slot.
Where it differs
Soul 2 is the newer Soul. It can also edit a picture you attach. Soul Standard starts from text only.
FAQ
Can I start from a picture?
No. Soul Standard takes a prompt only. Use Soul 2 when you want to edit a picture.
What resolutions does it offer?
720p and 1080p.
Who makes it?
Higgsfield.
Official sources
More image models
All image modelsZ-Image
Tongyi's efficient image model. Photoreal pictures and bilingual type from a prompt. On Visxy it does not take a picture to edit.
Qwen
The first Qwen image model from Alibaba. Strong type in the picture, plus one attached picture to edit or to transform.
Qwen Image
Qwen Image changes one picture you attach, using your prompt. It does not start from text alone.
Nano Banana 2.1
Google's newer Gemini image model, an update of Nano Banana 2. Sharper pictures and type, still a prompt plus up to four pictures you name.
Nano Banana Pro
Google's studio Gemini image model. Use it when type, a dense layout, or a product has to stay exact, not while you are still trying ideas.
GPT Image 2.6 Flare
OpenAI's faster GPT Image 2.6 model. More frame sizes, a quality choice from Low through Max, and edits of up to four pictures.