Model reference · open weights
tiny-wan22-vace-modular-pipe is an open-weight image model from akshan-main. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | akshan-main |
|---|---|
| Type | Image models |
| Task | Text→image |
| Parameters (lead) | 0M |
| Runs with | diffusers |
| Released | 2026-08-09 |
| Popularity | 959 downloads / month |
| Licence | Unknown |
About
This is a modular diffusion pipeline built with 🧨 Diffusers' modular pipeline framework.
Pipeline Type: Wan22VaceBlocks
Description: Modular pipeline for controllable video generation using Wan2.2 VACE.
This pipeline uses a 5-block architecture that can be customized and extended.
[TODO]
This modular pipeline is composed of the following blocks:
WanTextEncoderStep)
WanVaceEncoderStep)
Wan22VaceCoreDenoiseStep)
WanVaceTrimReferenceLatentsStep)
WanVaeDecoderStep)
UMT5EncoderModel)AutoTokenizer)ClassifierFreeGuidance)WanVACETransformer3DModel)AutoencoderKLWan)VideoProcessor)UniPCMultistepScheduler)ClassifierFreeGuidance)WanVACETransformer3DModel)boundary_ratio (default: 0.875): The boundary ratio to divide the denoising loop into high noise and low noise stages.
Inputs:
prompt (None, optional): No description providednegative_prompt (None, optional): No description providedmax_sequence_length (None, optional, defaults to 512): No description providedvideo (list, optional): The control video to condition the generation on. If not provided, an empty video is used.mask (list, optional): The mask that defines which video regions to condition on (black) and which to generate (white). Can only be passed if video is passed as well.reference_images (Image | list, optional): One or more reference images as extra conditioning for the generation.conditioning_scale (float | list | Tensor, optional, defaults to 1.0): The conditioning scale applied in each control layer of the model. If a float, it is applied uniformly to all layers; a list or tensor must have the same length as the number of control layers.height (None, optional): No description providedwidth (None, optional): No description providednum_frames (int, optional, defaults to 81): No description providedgenerator (None, optional): No description providednum_videos_per_prompt (None, optional, defaults to 1): No description providednum_inference_steps (None, optional, defaults to 50): No description providedtimesteps (None, optional): No description providedsigmas (None, optional): No description providedlatents (Tensor | NoneType, optional): No description providedattention_kwargs (None, optional): No description providedoutput_type (str, optional, defaults to np): The output type of the decoded videosOutputs:
videos (list): The generated videos.From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys tiny-wan22-vace-modular-pipe for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (tiny-wan22-vace-modular-pipe below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tiny-wan22-vace-modular-pipe","prompt":"a red bicycle","size":"1024x1024"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.