FlopGen
Sign in with Google
FlopGen

The multi-engine generative-media platform.

One hook. Every engine. Pick the one you like, or run them all and compare. Pay in FLOP.

76 models · 70 commercial-ready · 7 live now

Video23 models

Talking heads

Portrait + a voice track, animated into a speaking clip.

FantasyTalking Alibaba AMAP
portrait + audio (+ optional motion prompt); Wan2.1-14B; PROVEN on RunPod
image-to-videotalking-head-animationaudio-drivenlip-sync
Apache-2.0 (adapter + Wan2.1 base)
50 FLOP Commercial preview model card
Hallo3 Fudan
portrait + audio + scene prompt; long-clip, full-scene motion; H100-class
image-to-videotalking-head-animationaudio-drivenlip-sync
MIT (code); CogVideoX-5B weights, verify commercial
55 FLOP Commercial preview model card
SadTalker Tencent / XJTU
portrait + audio; fast warp/3DMM, runs on modest GPU or CPU
image-to-videotalking-head-animationaudio-drivenlip-sync
Apache-2.0 (code); bundles Wav2Lip NON-COMMERCIAL
15 FLOP Research only preview model card
EchoMimic Ant Group
portrait + audio (+ optional landmarks/pose); SD1.5 / AnimateDiff
image-to-videotalking-head-animationaudio-drivenlip-sync
Apache-2.0 (code); weights research disclaimer, verify
25 FLOP Commercial preview model card
Sonic Tencent
portrait + audio; high quality, Stable-Video-Diffusion based
image-to-videotalking-head-animationaudio-drivenlip-sync
CC BY-NC-SA 4.0 (NON-COMMERCIAL); SVD base
25 FLOP Research only preview model card
AniPortrait Tencent Games
portrait + audio; SD1.5 / AnimateDiff, 512x512, strong identity
image-to-videotalking-head-animationaudio-drivenlip-sync
Apache-2.0 (code); SD1.5 OpenRAIL-M base, verify
25 FLOP Commercial preview model card

Reenactment

Portrait + a driving performance video; real motion copied.

LivePortrait Kuaishou
portrait + driving video; near real-time, warp-based, high quality
image-to-videoface-reenactmentvideo-drivenreal-time
MIT (code); swap out InsightFace detector to stay clean
20 FLOP Commercial preview model card
FlashPortrait Fudan + MSRA
portrait + driving video; Wan2.1-14B, infinite-length ID-preserving
image-to-videoface-reenactmentvideo-driven
Apache-2.0 (code + Wan2.1 base)
40 FLOP Commercial preview model card

Face swap

A face mapped onto existing footage. No training, per clip.

FaceFusion Henry Ruhs
source face + target video; headless onnxruntime; pin hyperswap (not inswapper)
image-to-videoface-swap
OpenRAIL-AS (code); default hyperswap weights commercial-ok
15 FLOP Commercial preview model card
GHOST (sber-swap) Sber AI
source face + target video; one-shot, no per-face training
image-to-videoface-swap
Apache-2.0 (code + Sber weights)
15 FLOP Commercial preview model card
SimSwap SJTU
source face + target image/video; one-shot 224/512
image-to-videoface-swap
CC BY-NC 4.0 (NON-COMMERCIAL)
14 FLOP Research only preview model card
Deep-Live-Cam hacksider
source face + target video, or real-time webcam swap
image-to-videoface-swapreal-time
AGPL-3.0 (code); inswapper_128 weights NON-COMMERCIAL
18 FLOP Research only preview model card
DeepFaceLab iperov
cinematic quality; TRAINS per face-pair (hours-days), not on-demand
image-to-videoface-swap
GPL-3.0 (code); you train your own weights
60 FLOP Commercial preview model card

Character swap / body

The WHOLE person - face, hair, body, clothes. Replace the person in a video, or animate a reference person from a photo + motion.

Wan-Animate Alibaba Wan
replace the WHOLE person in a video with your character (Mix mode), keeps motion + expression; Wan2.x-based
image-to-videocharacter-swapvideo-driven
Apache-2.0 (Wan)
55 FLOP Commercial preview model card
Wan VACE Alibaba Wan
unified video edit: actor replacement, masked-region repaint, background swap; Wan2.1-based
image-to-videocharacter-swapvideo-driven
Apache-2.0 (Wan)
50 FLOP Commercial preview model card
MimicMotion Tencent
reference person photo + pose video -> full-body motion clip; SVD-based, ~16GB VRAM
image-to-videocharacter-swappose-driven
Apache-2.0 (code); Stability SVD base = NON-COMMERCIAL
45 FLOP Research only preview model card
MusePose (Animate Anyone) Tencent Music / Lyra Lab
reference person + driving pose -> animated; MusePose = the open Animate-Anyone reimpl
image-to-videocharacter-swappose-driven
MIT (code); SD1.5 + AnimateDiff OpenRAIL-M base
45 FLOP Commercial preview model card
UniAnimate Alibaba + HUST
reference person + pose; efficient long-video (1 min) human animation
image-to-videocharacter-swappose-driven
NON-COMMERCIAL (research only); SD2.1 base
40 FLOP Research only preview model card
Animate-X Ant Group
universal character animation (robust to stylized/anthropomorphic refs), pose-driven
image-to-videocharacter-swappose-driven
Apache-2.0 (code); SD2.1 OpenRAIL-M base
40 FLOP Commercial preview model card
EchoMimic V2 Ant Group
semi-body avatar, audio + pose driven (talks and gestures); ~16GB VRAM
image-to-videocharacter-swappose-drivenaudio-driven
Apache-2.0 (code + weights); SD1.5 OpenRAIL-M base
40 FLOP Commercial preview model card

Generators

Full generation from a prompt (or an image seed).

Wan 2.2 i2v A14B Alibaba Wan
image-to-video, ~5s, needs init_image
image-to-video
Apache-2.0
40 FLOP Commercial preview model card
Wan-Alpha (transparent) Wan + community DoRA
RGBA transparent video, ~5s
image-to-videotransparent-output
Apache-2.0
45 FLOP Commercial preview model card
Wan 2.2 FLF (first-last frame) Alibaba Wan
first + last frame conditioning, ~5s; needs init_image + last_frame
image-to-video
Apache-2.0
42 FLOP Commercial preview model card

Image32 models

Generators

Full generation from a prompt (or an image seed).

Stable Diffusion XL Stability AI
1024x1024 (portrait/landscape ok)
text-to-imagepainterly
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
Juggernaut XL RunDiffusion
1024x1536
text-to-imagephotorealisticpainterly
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
DreamShaper XL Lykon
1024x1536
text-to-imagepainterly
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
RealVisXL V5 SG161222
1024x1536
text-to-imagephotorealistic
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
ZavyChroma XL Zavy
1024x1536
text-to-imagepainterly
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
EpicRealism XL epinikion
1024x1536
text-to-imagephotorealistic
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
Playground v2.5 Playground AI
1024x1024
text-to-imagepainterly
Playground v2.5 Community
5 FLOP Commercial preview model card
Kolors Kuaishou
1024x1024
text-to-imagepainterly
Apache-2.0
5 FLOP Commercial preview model card
FLUX.1 dev Black Forest Labs
1024x1536
text-to-imagepainterly
FLUX.1-dev Non-Commercial
8 FLOP Commercial preview model card
Qwen-Image Alibaba Qwen
1024x1536
text-to-imagepainterly
Apache-2.0
6 FLOP Commercial preview model card
SANA 1.6B NVIDIA
1024x1024 (fast)
text-to-image
NSCLv2
4 FLOP Commercial preview model card
PixArt-Sigma PixArt-alpha
1024x1024
text-to-imagepainterly
OpenRAIL++
4 FLOP Commercial preview model card
AbsoluteReality (SD1.5) Lykon
512x768
text-to-imagephotorealistic
CreativeML OpenRAIL-M
3 FLOP Commercial preview model card
Realistic Vision V6 (SD1.5) SG161222
512x768
text-to-imagephotorealistic
CreativeML OpenRAIL-M
3 FLOP Commercial preview model card
DreamShaper 8 (SD1.5) Lykon
512x768
text-to-imagepainterly
CreativeML OpenRAIL-M
3 FLOP Commercial preview model card
Stable Diffusion 3.5 Large Stability AI
1024x1024, gated weights
text-to-imagepainterly
Stability AI Community
6 FLOP Commercial preview model card
Stable Image Ultra Stability AI
hosted API, top-tier 1MP+
text-to-imagepainterly
Proprietary (Stability API)
14 FLOP Commercial preview model card
HiDream-I1 Full HiDream AI
1024x1024, needs a Llama text encoder
text-to-imagepainterly
MIT
6 FLOP Commercial preview model card
HunyuanImage 3.0 Tencent
native multimodal, 1024x1024+
text-to-imagepainterly
Tencent Hunyuan Community
7 FLOP Commercial preview model card
Z-Image Tongyi Lab (Alibaba)
6B efficient, 1024x1024
text-to-imagepainterly
Apache-2.0
4 FLOP Commercial preview model card
Z-Image Turbo Tongyi Lab (Alibaba)
few-step distilled, fast 1024x1024
text-to-image
Apache-2.0
3 FLOP Commercial preview model card
Imagen 4 Google
high-fidelity text-to-image
text-to-image
Proprietary (Vertex API)
10 FLOP Commercial preview model card

Pixel art

Low-resolution retro sprite art, by design.

Retro Diffusion (RD Pro) Retro Diffusion
true pixel art, up to 256px
text-to-imagepixel-art
Commercial (RD API)
4 FLOP Commercial preview model card
Pixel Art XL (SDXL LoRA) nerijs
1024x1024 + kCentroid downscale
text-to-imagepixel-art
CreativeML OpenRAIL++
5 FLOP Commercial preview model card
Pixel Art Redmond (SDXL) ArtificialGuyBr
1024x1024
text-to-imagepixel-art
CreativeML OpenRAIL++
5 FLOP Commercial preview model card

Instruction edit

Redraws an image you supply from a text instruction.

Nano Banana (Gemini 2.5 Flash Image) Google
instruction image edit + generation; needs init_image for edits
instruction-editimage-to-image
Proprietary (Vertex / Gemini API)
10 FLOP Commercial live model card
GPT Image 2 OpenAI
top-tier image gen + instruction edit, up to 2K
instruction-editimage-to-image
Proprietary (OpenAI API)
12 FLOP Commercial preview model card
Qwen-Image-Edit Alibaba Qwen
instruction edit, needs init_image
instruction-editimage-to-image
Apache-2.0
7 FLOP Commercial preview model card
FLUX.1 Kontext dev Black Forest Labs
instruction edit, needs init_image
instruction-editimage-to-image
FLUX.1 Non-Commercial
9 FLOP Commercial preview model card
Step1X-Edit StepFun
instruction edit, needs init_image
instruction-editimage-to-image
Apache-2.0
6 FLOP Commercial preview model card
InstructPix2Pix Tim Brooks et al.
instruction edit, needs init_image
instruction-editimage-to-image
MIT
3 FLOP Commercial preview model card

Vector / SVG

Returns scalable SVG, not a raster bitmap.

FlopSVG (text-to-vector) FlopCoin (self-hosted)
prompt -> catalog image model -> vector tracer (vtracer/potrace/pngtosvg) -> SVG
text-to-imagetext-to-vectorsvg-output
MIT (first-party)
6 FLOP Commercial preview model card

Audio3 models

ACE-Step v1 3.5B ACE Studio / StepFun
music, up to ~4 min
audio-generationmusic
Apache-2.0
8 FLOP Commercial preview model card
Stable Audio Open Stability AI
sound effects, up to ~47s
audio-generationsound-effects
Stability Community
6 FLOP Commercial preview model card
TangoFlux Declare Lab
sound effects, ~10s
audio-generationsound-effects
Non-Commercial (research)
5 FLOP Commercial preview model card

Text & vision18 models

Llama 3.2 3B Meta
128k context, fast
text-generationchat
Llama 3.2 Community
1 FLOP Commercial live model card
Llama 3.3 70B Meta
128k context, flagship open
text-generationchat
Llama 3.3 Community
5 FLOP Commercial preview model card
Llama 3.1 8B Meta
128k context, balanced
text-generationchat
Llama 3.1 Community
2 FLOP Commercial preview model card
Qwen2.5 72B Alibaba Qwen
128k context, top open general
text-generationchat
Qwen License
5 FLOP Commercial preview model card
Qwen2.5 Coder 32B Alibaba Qwen
code-specialized
text-generationcode-generation
Apache-2.0
4 FLOP Commercial preview model card
DeepSeek-R1 70B DeepSeek
reasoning / chain-of-thought
text-generationreasoning
MIT
5 FLOP Commercial preview model card
Mistral Small 3 24B Mistral AI
32k context
text-generationchat
Apache-2.0
3 FLOP Commercial preview model card
Gemma 3 4B (vision) Google
multimodal text + vision (i2text); self-hosted vLLM on RunPod
text-generationchatimage-understanding
Gemma
3 FLOP Commercial live model card
Phi-4 14B Microsoft
small but strong
text-generationchat
MIT
2 FLOP Commercial preview model card
Llama 3.2 Vision 11B Meta
image understanding (i2text); self-hosted vLLM on RunPod
text-generationimage-understanding
Llama 3.2 Community
6 FLOP Commercial live model card
Qwen2.5-VL 7B Alibaba Qwen
image + document understanding (i2text); self-hosted vLLM on RunPod
text-generationimage-understanding
Apache-2.0
6 FLOP Commercial live model card
LLaVA 1.6 (Mistral 7B) LLaVA
lightweight vision-language (i2text); self-hosted vLLM on RunPod
text-generationimage-understanding
Apache-2.0
2 FLOP Commercial live model card
Claude Opus 4.8 Anthropic
frontier reasoning + vision, 200k+ context
text-generationchatreasoningimage-understanding
Proprietary (Anthropic API)
30 FLOP Commercial preview model card
Claude Fable 5 Anthropic
frontier creative writing
text-generationchatcreative-writing
Proprietary (Anthropic API)
22 FLOP Commercial preview model card
Claude Sonnet 5 Anthropic
balanced frontier, fast
text-generationchatreasoningimage-understanding
Proprietary (Anthropic API)
12 FLOP Commercial preview model card
Claude Haiku 4.5 Anthropic
fast + cheap frontier
text-generationchat
Proprietary (Anthropic API)
6 FLOP Commercial preview model card
GPT-4o OpenAI
multimodal frontier + vision (text + image-to-text)
text-generationchatimage-understanding
Proprietary (OpenAI API)
18 FLOP Commercial live model card
Gemini 2.5 Pro Google
long-context multimodal, 1M tokens
text-generationchatimage-understanding
Proprietary (Google API)
16 FLOP Commercial preview model card