Veda is a learned sparse-attention method with a ComfyUI integration for MiniMax H3. It aims to reduce attention computation by predicting which regions are important and computing a selected subset. It is not a new video model, a Turbo LoRA, or a guarantee that every local workflow becomes faster by the same amount.
The useful questions are practical: where does the node belong, what predictor does it require, and what should you check when references or audio matter? This explanation follows the project README and predictor model card, first reviewed on October 8 and checked again on October 12, 2026. We have not installed Veda or reproduced its performance. H3Vid does not expose an attention-backend selection in its hosted generator.
Veda changes computation, not the creative brief
A Turbo LoRA changes the model through learned weights for a different sampling recipe. Veda instead changes how attention is calculated. Its small predictor estimates which attention tiles to retain. The author's default configuration targets skipping roughly 90% of candidate attention tiles; this is not a claim that 90% of the entire generation workload disappears.
A video run still includes other work: model movement, sampling operations outside attention, decoding, and delivery. If one of those dominates your system, a faster attention stage may produce a smaller total improvement. Separate attention timing from the time between clicking Generate and receiving a usable clip.
Keep the prompt, references, and sampling configuration stable during your first comparison. Changing the scene and enabling Veda simultaneously makes it harder to identify why the result or timing changed.
Documented installation and placement
The current node documentation requires ComfyUI 0.38.0 or newer and offers installation through the Comfy Registry. It also provides templates for H3 text-to-video and reference-to-video. For an existing graph, the node sits on the MODEL connection after model and LoRA loading, immediately before the guider or sampler.
The separate predictor is stored in ComfyUI/models/veda/. The documented filename is:
minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors
A template's missing-model dialog can offer this file. The node itself does not silently download it; a missing selection should produce an explanatory message. Check that the selected file appears in the predictor list before diagnosing an apparent lack of speedup.
Read the current installation instructions for your environment. They distinguish NVIDIA kernel dependencies from the Apple Silicon route. Preserve a working baseline graph before modifying it, and keep the revision you installed with your test notes. These are documentation-based instructions, not a verified installation transcript.
What T2VA and 8NFE in the name mean
The predictor's repository name describes its training configuration. The model card says it can also be used with first/last-frame and reference generation, and with other diffusion-step counts. That permission to try a configuration is different from evidence that it performs equally well in every configuration.
The ComfyUI README identifies training around an eight-step Turbo recipe and a defined set of sizes and durations. Other combinations require comparison against full attention. As of October 10, 2026, a dedicated R2VA preview predictor is available, and the current ComfyUI README lists minimax_h3_r2va_veda_preview_fp8.safetensors for its reference template. This updates the earlier announcement's future-release language. The R2VA card describes an eight-step Turbo setup with independently selected visual-reference and generated-video tiles, while text and audio attention remain dense. Its comparison videos reuse the Dense audio track, so those paired videos do not independently demonstrate the sparse run's audio quality. Choose the predictor for the intended task and compare against full attention; availability alone does not validate every reference workflow.
For a character-reference workflow, judge identity and small features directly. A result that is pleasing as a standalone shot may still miss the specific facial details, clothing, or object geometry that motivated the reference input.
Generated and reference attention have separate controls
Veda exposes separate sparsity settings for generated content and reference content. The current defaults use the selected predictor's trained budget. A percentage describes skipped tiles; an integer describes a fixed number of retained 128-token key tiles. Those are different units. The node documentation describes a zero reference-sparsity setting as full attention for those references. It also provides ways to retain full attention on selected layers or sampling steps.
Treat these as controls to investigate a particular failure, not universal magic values. If a reference feature disappears, keep the source and seed fixed and compare a baseline, the current sparse configuration, and a configuration that preserves more reference attention. Inspect the exact feature you care about at several moments.
Do not assume every attention patch in a graph stacks productively. The project warns that ComfyUI's own Model Sparse Attention replacement can prevent Veda from being called. Read the current compatibility section for other patches and inspect the node's status text. An enabled box is not proof that a sparse kernel actually ran.
AMD and Apple Silicon now have upstream paths
As checked on October 12, the upstream node documents Triton INT8 for NVIDIA SM80 and newer, AMD RDNA3/RDNA4 on ROCm, and an MLX path for Apple Silicon. The hardware validation log distinguishes tested hardware from ready code paths. It records RX 9060 XT kernel checks on Windows and M3 Pro kernel self-tests; those checks do not establish full video-generation speed or quality on every Radeon or Mac.
ROCm Ninodes remains a separate Strix Halo / gfx1151 integration. Do not transfer its measurements to an upstream RDNA4 path or assume that a kernel self-test demonstrates an entire local video pipeline. Select the documentation for the node you installed and confirm its reported backend. We have not installed either AMD route or the MLX route.
The same upstream log now records reference and two-stage comparisons, including configurations where sparse attention was not faster at small token counts. Its expanded samples did not support the suspected periodic reference-tile artifact. That narrows one reported problem; it is not proof of universal reference identity or audio equivalence. The R2VA model-card comparison's reused Dense audio remains a separate limitation when evaluating sound.
Read speed claims in their measurement context
The model card gives author-reported acceleration claims and side-by-side examples. A community report describes one laptop configuration taking 8:05 without Veda and 4:32 with it, using a four-step LoRA and a 15-second, 1344×768 clip. The same discussion includes conflicting quality and comparison experiences. These are reports from other people, not project benchmarks.
A laptop GPU, a desktop GPU, and a unified-memory machine are different execution environments. Keep hardware, precision, offloading, other patches, and cold versus warm loading visible when comparing measurements. A timing for one prompt does not establish an overall ranking against SoL, SLA, Spectrum, or another acceleration method.
A useful local comparison checklist
Use the same source inputs and seed for each pair. Record the model checkpoint, LoRA and strength, sampling schedule, dimensions, duration, attention patches, and selected predictor. Run once to identify loading effects, then label subsequent measurements clearly as warm runs.
Review complete playback and matched frames. Check motion, identity, fine structures, scene continuity, and sound. Listen for distortion and compare synchronization where visible actions have audible consequences. Note peak memory if you can measure it consistently.
Repeat with more than one scene before drawing a general conclusion. A static portrait, a moving subject, and a reference-driven interaction stress different parts of a workflow. Keep the conclusion narrow when your evidence is narrow: for example, a measured improvement for one hardware configuration and task, with an explicit quality review.
For the wider local setup, see MiniMax H3 in ComfyUI. For distilled model choices, see FastH3 V2 and Trim. Veda is an execution technique to evaluate within that stack; choosing it does not replace choosing the right model and task.
The cover is an AI-generated concept illustration, not a Veda visualization, generated-video sample, or performance result.