Workflows & Models
OpenFork workflows are Docker-backed GPU services. The website, desktop app, Python client, and cloud images all read from the same service registry so model availability, VRAM requirements, and routing stay aligned.
52
Enabled services
74
Workflow entries
2GB
Lowest VRAM
32GB
Highest VRAM
services.json. Workflow processors and workflow JSON live in the Python client.Video
Text-to-video, image-to-video, video-to-video, and native audio-video generation.
daVinci MagiHuman
daVinci-MagiHuman through Wan2GP with Magi Human Distill SR1080 quanto int8 weights. Requires a start image.
DreamID-Omni
DreamID-Omni FP8 talking-head video with identity and voice reference inputs
Hunyuan 1.5
Tencent's SOTA FP8 video model
LTX-2.3
LTX-2.3 22B: native audio+video generation (24GB)
SCAIL
Experimental 16GB SCAIL 14B through Wan2GP for pose-guided character animation at reduced resolution and duration.
TurboDiffusion
Real-time prototyping video model
Vista4D
Vista4D 384p49 through Wan2GP for source-video novel-view reshooting with predefined camera trajectories.
WAN 2.2
High-quality video (Text/Image-to-Video)
Image
Text-to-image, instruction editing, inpainting, and illustration models.
Anima
Anima text-to-image illustration model
ERNIE-Image
Baidu ERNIE-Image text-to-image (FP16)
FLUX Kontext
FLUX.1 Kontext [dev] GGUF Q4_K_M for 8GB VRAM; supports optional two-image composition by precomposing the source and identity reference
Qwen Edit
Qwen-Image-Edit-2511 instruction-based image editing
Qwen Turbo
Ultra-fast instruction-based editing with an optional second reference image (2 steps)
Z-Image
High-quality Z-Image (Q4_K_M GGUF)
Z-Image Turbo
ControlNet & Flux Image Gen
Audio
TTS, voice clone/design, music, sound effects, foley, and speech restoration.
ACE-Step 1.5
ACE-Step 1.5 XL music generation for 16GB VRAM
AudioX
AudioX text-to-audio and video-conditioned sound generation
Chatterbox
High-quality voice cloning
DiffRhythm
AI-powered music composition
HeartMuLa
4-bit quantized music generation (~8GB VRAM)
MMAudio V2A
Video-to-audio synthesis (MMAudio small_44k)
PRiSM Audio
High-fidelity video-to-audio generation (PRiSM)
Qwen3-TTS
Alibaba's multilingual TTS with 9 premium voices
Qwen3-TTS 1.7B
Alibaba's multilingual TTS with voice design (1.7B)
Speech Enhancement
High-efficiency speech restoration and enhancement
Stable Audio
Sound FX and text-to-audio
VibeVoice
Clone-ready text-to-speech
Utilities
Upscaling, prompt helpers, and local utility services used by production workflows.
LLM
Qwen3 4B for workflow planning, scripts, prompts, and dialogue
SparkVSR
State-of-the-art video super-resolution (24GB VRAM required)
How Jobs Run
Submit
The website creates a DGN job with workflow type, inputs, storage target, policy, and billing plan.
Route
The orchestrator chooses a capable provider, preferring cached images and policy-compatible providers.
Process
The Python client pulls the Docker image if needed, runs the processor, uploads outputs, and settles credits or paid earnings.
Job Policies
Choose private, trusted, public, or paid routing