ourdream
NSFW image and video generator. Prompts, negative prompts, LoRAs, 4K output. Characters keep their face across renders.
Provisional score. Built from documented features, current pricing, published reviews. Full bench run on a paid account is queued. Score will move; we'll log the delta here.

Verdict
Leads on every measure: free-form prompting, video, and faces that stay consistent across a set. Ten free generations to start.
Wins
- Image and video generation with full prompts, negative prompts and LoRAs
- Character consistency holds across images and video
- 4K output, voice, chat included; ten free generations to start
Loses
- Subscription model means occasional users pay for unused time
- Character layer adds steps when you only need one quick image
What it is
A standalone NSFW image and video generator at ourdream.ai/generator. Prompt and negative-prompt fields, LoRA support, 4K output, video. It sits next to a roleplay platform that draws on the same engine. Prompt from scratch or generate from a character you have built.
Where it stands out
The only tool here that scores well on prompt control and consistency both. Studios hand you the prompt box and lose the face between renders. Companion apps keep the face and strip out the prompt box. ourdream keeps both. Adds video and voice.
Where it falls short
Subscription, not credits. A once-a-month user pays for the full month. And if you only want one quick image, the character tools remain visible. Extra steps you can skip.
Who it is for
Anyone who wants to prompt freely and keep a character consistent across images and video. Ten free generations let you test the output before paying.
Pricing
| 1 month | $19.99 |
| Annual around $119.88 |
Compare and swap
What each reading means
- Realism (22%)
- Skin, hands, lighting and anatomy on the same prompt set. Photoreal when asked, stylised when asked.
- Prompt control (17%)
- How much of the result you steer: model choice, reference images, LoRAs, negative prompts, seeds, inpainting.
- Consistency (15%)
- Same subject, four scenes, then video. Does the face, body and styling survive, or does each render produce a stranger?
- Freedom (18%)
- What the tool lets you make. Explicit content on by default, opt-in, or blocked, and how often moderation false-positives.
- Video (10%)
- Whether it does video at all, clip length, motion quality, and whether video is explicit-capable.
- Usability (6%)
- Time from sign-up to first good output, queue times, and whether the interface gets in the way.
- Value (12%)
- What a month of real use costs against what you get: credits, unlimited tiers, watermarks and free allowance.