black-forest-labs/flux-kontext-pro
Edit images using natural language text prompts with high-quality results and excellent prompt following. Performs style...
Found 84 models (showing 1-20)
Edit images using natural language text prompts with high-quality results and excellent prompt following. Performs style...
Generates images from text prompts with support for character reference consistency. Takes a text prompt and optionally...
Generate images from text prompts with accelerated processing while maintaining quality. Features advanced natural langu...
Generates images from text prompts with advanced natural language understanding and multi-image reference capabilities....
Generate identity-consistent images of a person from a reference face image and a text prompt. Preserve facial identity...
Generate images of a specific person from a face photo and a text prompt, preserving identity across new styles and scen...
Generate multi-view character images from a single input image. Produce 1 or 4 consistent views of the same subject acro...
Generate avatars of one or two people from face image(s) and a text prompt. Upload a front-facing selfie (optionally a s...
Generate new images of a referenced subject from a text prompt. Takes a reference image and prompt as inputs and outputs...
Edit images from text instructions, optionally combining up to three reference images to compose new results. Accepts on...
Generate identity-consistent images of a person from a face image and a text prompt. Condition generation on FaceID embe...
Swap outfits and backgrounds on a personβs photo and return an edited image. Provide a subject image, a clothing/style r...
Places a person from an input image into extreme and impossible scenarios like floating in space as an astronaut, swimmi...
Generate images of Vladimir Ilyich Lenin from text prompts. Use the LEN trigger token to invoke an SDXL LoRA fine-tuned...
Generate stylized couples portraits from two face reference images, a text prompt, and optional style, base, and depth i...
Generate multi-panel comics and consistent image sequences from text prompts. Provide a multi-line comic_description to...
Transform a personβs photo into stylized avatars in 3D, Emoji, Video game, Pixels, Clay, or Toy styles. Accepts a single...
Generate images of a specific person in new styles and scenarios from one or more input photos. Provide 1β4 human refere...
Generate photorealistic images of a person from a single reference photo and a text prompt, preserving identity across n...
Generate stylized portraits and avatars from one or more input photos of a person. Provide a text prompt that includes t...