Human-written demonstration (OpenAssistant volunteers)· OpenAssistant (human-written)
OpenAssistant Conversations (oasst2)
Give me a text2img prompt to generate a Ghibli wallpaper of a cozy cabin in a forest
In OpenAssistant data, “assistant” turns were written by human volunteers as demonstrations. They are not model outputs.
- User
Give me a text2img prompt to generate a Ghibli wallpaper of a cozy cabin in a forest
- Assistant
Studio Ghibli, Cozy Cabin, In A Forest, Bright Colors, Anime Illustration, Cinematic, Professional Lighting, Very Detailed Illustration, 8k
- User
Now tweak it for stable diffusion 1.5
- Assistant
Positive Prompt:
(hayao miyazaki, 宮崎 駿:1.5), (ghibli:1.5), cinematic lighting, (cabin, cottage, colonial style:1.2), forest, woods, path, (clearing:0.8), (dappled:1.4), (anime:2.0)Negative Prompt:
lowres, (bad anatomy), bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, photograph,This prompt is intended for the base stable diffusion 1.5 model, but I highly recommend you consider an anime derivative if you want to generate something in an Ghibli style, since you'll be able to achieve better results. If you do, make sure to remove
(anime:2.0)from the end.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →
- Human-written demonstration (OpenAssistant volunteers)Compare side by side →