change-camera-angle | Change Camera Angle | 1 | Camera-aware editing via fal.ai Qwen Image Edit 2511 with multi-angle LoRA. 360° orbit, tilt, and zoom. |
consistent-characters | Consistent Characters | 1 | Generate consistent character variations with FLUX Kontext, Nano Banana Pro/2, Flux 2 Dev, or Qwen Image 2 Pro. |
creative-upscale | Creative Upscale | 0.5 | Clarity Upscaler (creative upscale) via Replicate. Boost detail with stable-diffusion refinement. |
dreamina | Dreamina 3.1 | 1 | ByteDance Dreamina 3.1. 4MP cinematic text-to-image with precise style control. |
ernie | Ernie | 1 | Baidu Ernie text-to-image (fal.ai). Multilingual prompts and built-in prompt expansion. |
face-enhance | Face Enhance | 2 | Crystal Upscaler via Replicate. Face-detail preserving upscale, cost scales with output megapixels. |
flux | FLUX | 1 | FLUX family on Replicate. Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint. |
flux-2-flex | Flux 2 Flex | 1.5 | Max-quality with up to 10 reference images |
flux-2-klein-4b | Flux 2 Klein 4B | 0.1 | Very fast generation and editing with up to 5 reference images |
flux-2-klein-9b | Flux 2 Klein 9B | 0.5 | 4-step distilled FLUX.2 [klein] foundation model for flexible control |
flux-2-pro | Flux 2 Pro | 1.5 | High-quality with up to 8 reference images |
flux-2-max | Flux 2 Max | 2 | The highest fidelity image model from Black Forest Labs |
flux-2-dev | Flux 2 Dev | 1 | Fast quality with up to 4 reference images |
flux-2-lora | Flux 2 Dev + LoRA | 1 | Dev model with custom LoRA support |
flux-edit | Flux Edit (Kontext) | 1 | Black Forest Labs FLUX.1 Kontext for text-driven image editing. Dev (open-weight), Pro (state-of-the-art), and Max (premium typography). |
flux-dev | Flux Dev | 1 | High-quality development model with configurable steps, guidance, and LoRA support. |
flux-krea-dev | Flux Krea Dev | 1 | Photorealistic generation that avoids the oversaturated AI look. LoRA compatible. |
flux-dev-multi-lora | Flux Dev Multi LoRA | 1 | Supports multiple custom LoRAs simultaneously for complex style combinations. |
flux-1.1-pro | Flux 1.1 Pro | 1 | Latest pro model with enhanced quality and strong prompt adherence. |
flux-1.1-pro-ultra | Flux 1.1 Pro Ultra | 1.5 | Highest quality Flux model with raw mode for natural-looking images. |
flux-kontext-pro | Flux Kontext Pro | 1 | Advanced model with state-of-the-art performance for both generation and editing. |
flux-kontext-max | Flux Kontext Max | 2 | Premium model with maximum performance and improved typography for generation and editing. |
gemini-flash | Google Gemini Flash | 1 | Fast generation with Gemini 2.5 Flash |
nano-banana-pro | Google Nano Banana Pro | 3 | SOTA with accurate typography and reasoning |
nano-banana-2 | Google Nano Banana 2 | 3 | Next-generation SOTA model with stronger consistency |
google-nano-banana | Nano Banana Edit | 3 | Google Nano Banana image editing. Multi-image fusion + edit instruction with Standard/Pro/Pro-fal tiers and 1K/2K/4K resolution. |
gpt-image-low | GPT-Image 1.5 Low | 1 | Fast, lower detail generation |
gpt-image-medium | GPT-Image 1.5 Medium | 1 | Balanced quality and speed |
gpt-image-high | GPT-Image 1.5 High | 4 | Maximum detail and quality |
gpt-image-1-5-edit | GPT-Image 1.5 Edit | 4 | OpenAI GPT-Image 1.5 image editing — supply 1-8 reference images plus an edit instruction. Optional transparent background and high-fidelity input mode. |
gpt-image-2 | GPT Image 2 | 5 | OpenAI GPT Image 2 via fal.ai — next-generation image model with 4K rendering and sharper text fidelity. |
gpt-image-2-edit | GPT Image 2 Edit | 5 | OpenAI GPT Image 2 image editing — supply 1-8 reference images plus an edit instruction. Optional mask for inpainting. 4K-capable; pricing varies by quality + size. |
hidream-l1-fast | HiDream L1 Fast | 1 | HiDream L1 Fast - Fast generation |
hidream-l1-dev | HiDream L1 Dev | 1 | HiDream L1 Dev - Fast generation |
hidream-l1-full | HiDream L1 Full | 2 | HiDream L1 Full - Highest quality |
hidream-e1.1 | HiDream E1.1 | 1 | HiDream E1.1 - Fast generation |
hidream-edit | HiDream E1.1 Edit | 1 | HiDream E1.1 — image-conditioned editing with prompt + reference image. Single image input. |
hunyuan-3d | Hunyuan 3D | 4 | Tencent Hunyuan 3D 3.1. Generate 3D meshes from a text prompt or a single image. |
ideogram-character | Ideogram Character | 5 | Generate consistent characters from a single reference image in many styles. |
image-editor | Character Stylist | 1 | One-shot FLUX Kontext variants — filters, cartoonify, iconic locations, haircut swap, headshots, renaissance, face-to-many, and more. |
image-relighting | Image Relighting | 1 | Relight images with Magic Lighting, Nano Banana Pro/2, or Qwen Image Edit — multi-provider routing with per-model credit rates. |
image-to-image-flux | Flux Image to Image | 1 | FLUX Dev LoRA image-to-image on Replicate. Prompt + source image + optional LoRA weights. |
imagineart | Imagineart | 1.5 | Imagineart 1.5 Pro image generation (fal.ai). |
kling-image | Kling Image V3 | 1 | Kling Image V3 (fal.ai). High-quality text-to-image with flexible aspect ratios. |
kling-image-edit | Kling Image Edit | 1 | Kling Image V3 (fal.ai) image-to-image editing with a text instruction. |
magnific-upscaler | Magnific Upscaler | 3 | Freepik Magnific upscaler. Creative or precision mode, up to 16x. |
openai-image-1 | OpenAI Image 1 | 1 | OpenAI GPT Image 1 Mini. Text-to-image via Replicate. |
openai-image-1-edit | OpenAI Image 1 Edit | 1 | OpenAI GPT Image 1 Mini image editing — combine 1-8 reference images with a text edit instruction. Supports transparent or opaque backgrounds. |
outpaint | Outpaint | 1 | fal.ai Image Apps V2 outpainting. Expand an image beyond its original edges. |
p-image | P-Image | 0.1 | Pruna P-Image. Sub-second text-to-image with optional custom dimensions. |
p-image-edit | P-Image Edit | 0.25 | Pruna P-Image Edit. Fast image editing with up to 5 reference images. |
ponyxl-ponyrealism-v23 | Pony Realism | 1 | Pony Realism - Stylized anime generation |
ponyxl-tponynai3-v7 | Pony NAI | 1 | Pony NAI - Stylized anime generation |
ponyxl-waianinsfwponyxl-v140 | Wai ANI | 1 | Wai ANI - Stylized anime generation |
qwen-image-plus | QWEN Image Plus | 1 | Fast generation with excellent quality |
qwen-image-max | QWEN Image Max | 2 | Highest quality output |
qwen-image-2.0 | QWEN Image 2.0 | 1 | Fast, balanced image generation and editing |
qwen-image-2.0-pro | QWEN Image 2.0 Pro | 2 | Enhanced text rendering, realistic textures, and semantic adherence |
qwen-image-2-edit | Qwen Image 2 Edit | 1 | Alibaba DashScope Qwen Image 2 edit — supply 1-3 reference images plus an edit instruction. Standard and Pro variants. |
qwen-image-edit | Qwen Image Edit | 1 | Alibaba DashScope Qwen Image edit — supply 1-3 reference images plus an edit instruction. Plus and Max model variants. |
recraft-v4 | Recraft V4 | 1 | Recraft's latest image model. Strong prompt accuracy, art-directed composition, integrated text rendering. Fast and cost-efficient at standard resolution. |
recraft-v4-pro | Recraft V4 Pro | 6 | Recraft V4 at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work. |
recraft-v4-svg | Recraft V4 SVG | 2 | Production-ready SVG vector images from text. Recraft V4's design taste applied to vector output — clean geometry, structured layers, editable paths. |
recraft-v4-pro-svg | Recraft V4 Pro SVG | 8 | Detailed SVG vector graphics from text. Recraft V4 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, scalable to any size. |
redux-flux | Flux Redux | 1 | Black Forest Labs Flux Redux image variations — feed a source image, get stylistic riffs. |
seedream-3 | Seedream 3 | 1 | ByteDance Seedream 3 text-to-image via Replicate. |
seedream-4 | Seedream 4.5 | 1 | ByteDance Seedream 4.5 — new-generation image creation with superior aesthetics, text rendering, and up to 4K resolution. |
seedream-5-lite | Seedream 5 Lite | 1 | ByteDance Seedream 5.0 Lite — fast, high-quality image generation and editing with strong aesthetics and text rendering. |
wan-2.6-image | WAN 2.6 Image | 1 | Alibaba WAN 2.6 text-to-image with prompt enhancement and multi-image output. |
wan-2.6-image-edit | WAN 2.6 Image Edit | 1 | Alibaba WAN 2.6 image editing. Up to 4 reference images. |
wan-2.7-image | WAN 2.7 Standard | 1 | Faster Wan 2.7 image generation and editing |
wan-2.7-image-pro | WAN 2.7 Pro | 2 | Higher quality Wan 2.7 tier with 4K support for text-to-image |
wan-2.7-image-edit | WAN 2.7 Image Edit | 1 | Alibaba WAN 2.7 image editing. Standard and Pro tiers, supports 1-4 input images for fusion edits. |
wan-image | WAN 2.2 Image | 1 | Fast cinematic image generation (3-6 seconds) with up to 4MP output and optional LoRA support. |
xai-image | Grok Imagine | 1 | xAI Grok Imagine. Fast tier for quick iteration, Quality tier for higher fidelity at 1k or 2k. |
xai-image-edit | Grok Image Edit | 1 | xAI Grok image editing. Sync response (no polling). Provide an image URL and a text edit instruction. Optional quality tier for 1k/2k high-fidelity edits. |
z-image-turbo | Z Image Turbo | 0.5 | Super-fast 6B parameter text-to-image with great text rendering and LoRA support. |