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.
62
Enabled services
100
Workflow entries
2GB
Lowest VRAM
80GB
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. Use for realistic portrait talking-head/lip-sync shots only. Requires a realistic portrait start image; generates synchronized speech/audio from the text prompt.
DomainShuttle
DomainShuttle subject-driven image-to-video using Wan2.2-DomainShuttle-A14B; registered as an 80GB service because the closest published upstream requirement is Wan2.2 A14B inference
DreamID-Omni
DreamID-Omni FP8 talking-head video with identity and voice reference inputs
LTX-2.3 Official
Official LTX-2 ltx-pipelines two-stage text-to-video generation plus image-to-video generation with the LTX-2.3 22B dev checkpoint and a trained LoRA package. This is separate from the LTX-2.3 Wan2GP GGUF services.
SCAIL-2
Experimental SCAIL-2 14B WanGP candidate using the DeepBeepMeep int8 SCAIL-2 weights, SAM3 Magic Mask assets, and the native scail2_14B WanGP model type. Use for OpenFork 16GB smoke testing before production runs.
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 Turbo text-to-image with CPU offload for 8GB GPUs
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
Ideogram 4
Ideogram 4 text-to-image using NF4 weights with CPU offload and structured JSON layer prompts; true 16GB Vast smoke passed on 2026-06-09
Krea 2
Experimental Krea 2 Turbo GGUF Q3 text-to-image via ComfyUI-GGUF with Qwen3-VL text encoder and Qwen Image VAE
PiD
NVIDIA PiD 4x image super-resolution using the Flux/Z-Image-compatible VAE decoder path.
Qwen Edit
Qwen-Image-Edit-2511 instruction editing plus Qwen-Image-2512 character LoRA text-to-image inference
Qwen LoRA
Qwen-Image-2512 character LoRA text-to-image inference using the Unsloth Q4_K_M GGUF diffusion model for 24GB GPUs
Qwen Turbo
Ultra-fast instruction-based editing with an optional second reference image (2 steps)
TeleStyleV2
TeleStyleV2 content/style reference transfer on Qwen-Image-Edit-2509 with the TeleStyle and DMD LoRAs; upstream target is H100 80GB
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
dots.tts MF
Rednote HiLab dots.tts MeanFlow-distilled continuous TTS and zero-shot voice cloning, smoke tested on the 6GB image
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)
Scenema Audio
XML-driven expressive speech generation with zero-shot voice cloning
Speech Enhancement
High-efficiency speech restoration and enhancement
Stable Audio 3
Stable Audio 3 Small-SFX sound-effects-only text-to-audio
VibeVoice
Clone-ready text-to-speech
Utilities
Upscaling, prompt helpers, and local utility services used by production workflows.
LLM
Local Qwen3 4B LLM for workflow planning on low-VRAM providers
LTX-2.3 Official
Official Lightricks LTX-2 Trainer package with the LTX-2.3 22B dev checkpoint. Standard upstream training targets 80GB+ VRAM; this lane targets the upstream 32GB low-VRAM INT8 config. 24GB is not an official supported trainer target.
SparkVSR
State-of-the-art video super-resolution (24GB VRAM required)
How Jobs Run
Submit
Route
Process
Job Policies
Choose private, trusted, public, or paid routing