ComfyUI
Workflows by Model
HotMiniMax H3Video with audio from text, images or references
HotQwen Image 2.1Create images and edit photos with references
WanVideo from text or images, motion transfer
FLUXImage generation, editing and character variations
LTXVideo with synced audio from text or images
Qwen Image EditPhoto editing with text and image references
Krea 2Image creation, style transfer and reference edits
Z-ImageFast portraits and concepts from text
Popular & New Workflows
NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audio
NewP-H3-Image Reference EditEdit a photo guided by a reference image
HotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audio
HotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audio
HotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motion
Qwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference images
FLUX Klein Face SwapNatural, lifelike face swaps
SeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows
Trainer
Train a Model
NewMOSS-Image BaseImage generation, newly supported
NewFLUX.3 KleinImage generation, newly supported
HotKrea 2The most-trained image model
HotKrea 2 TurboFew-step image generation
HotQwen Image 2.1Image generation and editing
Z-Image TurboFast portraits and concept images
MiniMax H3Video with synchronized audio
Train & Deploy
Getting StartedYour first training job with Ostris AI Toolkit
DatasetsUpload and manage training datasets
InferenceRun your trained models in a playground or via API
DeploymentsServe your trained models as dedicated endpoints
Train More Models
Models
Image Models
NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4K
NewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGs
HotSeedream 5.0 Pro41% OFF · Reference edits with multilingual text
HotSeedream 4.520% OFF · Photoreal edits with brand consistency
HotWan 2.6 ImageInstruction-based image editing
FLUX.2Precise, photorealistic image edits
Nano Banana Pro77% OFF · Precise 2K to 4K visuals from sketches
Qwen Image EditLoRA-based, structure-aware image editing
Video Models
NewKling 4.010% OFF · Animate a still into a 3 to 30s clip
HotWan 3.0 Prime13% OFF · Fast clips from reference videos
HotSeedance 2.536% OFF · Longer, more consistent cinematic video
HotWan 3.0Clips from image, video and audio references
HotMiniMax H3Animate a first frame into a 5 to 15s clip
Wan 2.510% OFF · Fluid motion with native audio
FLUX 3 MaxClips from text, a still, or keyframes
Wan 2.6 FlashLifelike scenes from stills with dialogue sync
View More Models
MCPNew
API
Pricing
Seedance 2.5Hot
Seedream 5.5New

TRAINING & INFERENCE

DEDICATED ENDPOINTS

ACCOUNT

Run LoRAruncomfy/krea2

runcomfy/krea2

LoRAs *

LoRA #1

Path *

This list comes from LoRA Assets. Upload LoRAs there to see more options.

LoRA Scale

Prompt *

Width

Height

Guidance Scale

Sample Steps

Negative Prompt

Seed

Sampler

Idle

Your request will cost $0.045 per megapixel of generated image.

Click Generate to start

Results will appear here