From the model card
Fields below are copied from the tags and counters on the HuggingFace repository Lykon/dreamshaper-7 at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- Lykon
- Pipeline tag
- text-to-image
- Library
- Diffusers
- Weight formats
- safetensors
- License tag
creativeml-openrail-m— read the license file in the repo before relying on it- Language tags
- English (en)
- Downloads (HF counter at last fetch)
- 869,123
- Likes (HF counter at last fetch)
- 64
- Model card
- https://huggingface.co/Lykon/dreamshaper-7
Use cases
- Generating stylized portraits and character art
- Concept art and illustration for game or film pre-production
- Photo-realistic scene generation from text descriptions
- Anime and semi-realistic character design
- Baseline checkpoint for LoRA fine-tuning on custom styles
Pros
- Strong out-of-box quality for portraits and artistic subjects without heavy prompt engineering
- SD 1.5 base means wide ControlNet and LoRA ecosystem compatibility
- Supports both diffusers StableDiffusionPipeline and A1111 checkpoints
- Widely tested with hundreds of community LoRAs
Cons
- SD 1.5 base limits maximum resolution to 512×512 natively; SDXL alternatives produce sharper detail at higher res
- CreativeML OpenRAIL-M has use restrictions; not fully permissive
- Photorealism breaks down on non-Western facial features without specific prompting
- Superseded by SDXL and newer architectures for many benchmark metrics
Tags
diffuserssafetensorsstable-diffusionstable-diffusion-diffuserstext-to-imageartartisticanimedreamshaperenlicense:creativeml-openrail-mendpoints_compatiblediffusers:StableDiffusionPipelineregion:us