Singularity V2 is a community fine-tuned fusion of MiniMax H3 for video with sound. Its new release targets broader action coverage, closer prompt following and stronger style rendering. The important download detail is simpler: the published V2 file is a full INT8 checkpoint. The smaller pruned files beside it still carry V1.3 names.
This guide follows the author's model card, current file tree, and SGLang's H3 cookbook, reviewed October 22, 2026. These are documentation-based instructions. We have not generated a Singularity clip, and H3Vid's online generators do not currently execute it.
What changed in V2?
The author describes expanded action training, better control over subjects and environments, and improved photorealistic and CG styles. The card also reports a repair to audio-reference conditioning. These are release claims, rather than a controlled comparison against base H3 or other fine-tunes.
One detail needs particular care: the English card says audio references can adjust a character's “color tone.” That wording does not establish how voice identity, timbre or visual color responds. Treat the announcement as an audio-conditioning fix; use a short controlled example to establish what it means for your scene before relying on it for a production voice.
Singularity remains a fusion model, combining H3 checkpoint families and further training. It is different from FastH3 Omni's reference-conditioned distillation and from an ordinary style LoRA. Downloading it changes the transformer used by the workflow; it does not install the surrounding text encoder, video VAE or audio VAE.
Choose the correct file
The publisher's file listing currently distinguishes these builds:
| Checkpoint | Approximate download | Meaning |
|---|---|---|
Minimax-h3_Singularity_ref2va_v2_int8.safetensors | 34.0 GB | The newly listed V2 INT8 model |
Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors | 34.0 GB | Older full V1.3 INT8 model |
Minimax-h3_Singularity_ref2va_Pruned_v1.3_int8.safetensors | 21.0 GB | Older pruned V1.3 build |
Minimax-h3_Singularity_ref2va_v1.3_Pruned_w4a8.safetensors | 11.8 GB | Older V1.3 W4A8 build |
These decimal file sizes describe storage, not required VRAM. Model loading, activations, reference encoding and decoding add their own memory demands. A 34 GB file does not imply a 34 GB card is the minimum, or that a smaller card will finish at a particular speed.
When someone recommends a smaller Singularity download, check the complete filename and revision. A working V1.3 quantization is useful, but changing its label in a preset does not give it V2's training. Community GGUF repositories are separate distributions; verify their model lineage rather than assuming their newest upload is V2.
Prepare ComfyUI without changing everything at once
Begin with a working native MiniMax H3 ComfyUI installation. Keep a saved copy of the graph and the exact model selected before changing it. Place the chosen transformer in the diffusion-model directory expected by your loader, then explicitly reselect it after refreshing the model list.
Retain the compatible H3 text encoder and both VAEs. Start with the same input mode, reference order, duration and resolution that already work. The Singularity card advertises text, image, reference and video workflows, but the graph still has to supply the matching conditioning. The ref2va filename alone is not a wiring tutorial for every mode.
For faster inference, the author recommends minimax_h3_ref2v_turbo_4step_v0.1. Match the sampler recipe to that adapter. Simply reducing an ordinary high-step graph to four steps does not install distillation. Likewise, do not add PTD, VSA and multiple action adapters to the first validation run: that makes any failure difficult to attribute.
Write a prompt that makes the upgrade useful
The author's suggested limit is approximately 5,000 characters. It is a ceiling for focused direction, not a minimum length. Organize the scene around a subject, one action sequence, a setting, camera behavior and one intended visual style.
For example, an original evaluation brief could describe a courier entering a courtyard, stopping beneath a lantern and placing a sealed envelope on a table. Specify a continuous tracking shot, natural fabric movement, grounded footsteps and a restrained photorealistic look. The envelope's location and the courier's stopping point give you visible events to review.
Keep that brief unchanged when comparing checkpoints. Save each seed, graph, model revision and adapter weight beside its output. Review whether the requested actions happen in order, whether background people inherit the courier's clothing, and whether the face remains recognizable at a distance. Those observations are more useful than declaring one attractive frame the winner.
Running outside ComfyUI
SGLang documents Singularity as a hybrid FL/Ref fusion transformer override while retaining the official H3 model for encoders and VAEs. Its currently shown recipe names V1.3 files and uses an explicit hybrid variant. That is evidence for a specific runtime arrangement, not confirmation that V2 has passed the same checks.
Before replacing that filename with V2, inspect the runtime's current supported-weight list and release notes. Keep base assets and transformer overrides separate. The model card's repository license label also does not by itself establish the rights for every upstream component in a hosted deployment.
For a local first attempt, choose the exact V2 file, a known H3 graph and a short scene with clear events. For a hosted workflow today, use the actual model name shown by your generator; H3 Max and Singularity are different execution choices.
The cover is an imagegen concept illustration of model-file selection, not a Singularity result or interface screenshot.