A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent...
FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality. Pricing is based on the output...
FLUX.2 [dev], a 32B flow-matching transformer for generating and editing multiple images.
FLUX.2 max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet. Pricing is as follows, [per the...
FLUX.2 flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture. Pricing is as follows, [per the docs: We charge...
Illustrious-based anime checkpoint with strong character knowledge and booru-style tag prompting.
Illustrious-based anime checkpoint with a bold, high-contrast style.
Cyberrealistic Pony is a semi-realistic Pony model capable of SFW and NSFW portraits as well as scenery.
Illustrious-based checkpoint specialising in anthro and furry character art.
Pony-based checkpoint aimed at photorealistic output while keeping Pony's prompt understanding.
Photorealistic SDXL merge tuned for portraits, cinematic lighting and product shots.
FLUX.1 [dev], a 12B rectified-flow transformer for high prompt-adherence text-to-image.
Anime-oriented SDXL merge (Anything XL) covering illustration and character art.
Pony-based anime merge favouring clean linework and consistent character rendering.
The Pony base checkpoint, tuned for prompt adherence and character control via score tags.
SD 1.5 realism merge best known for East Asian portrait photography.
SD 1.5 photorealism checkpoint (Natural Sin) tuned for skin detail and natural light.
SD 1.5 photorealism checkpoint aimed at portraits and lifelike detail.
General-purpose SD 1.5 merge covering photoreal, art and illustration styles.
SDXL edition of DreamShaper, a broad general-purpose merge.
This model is mainly intended for Portraits and Full Body Anime-like pictures. Fantasy landscapes are decent.
Passthrough lane for any Civitai checkpoint: paste a model URL and it renders on that checkpoint.