ACE-Step v1's node-pack fragmentation turns out to be moot: ComfyUI ships
TextEncodeAceStepAudio/EmptyAceStepLatentAudio as native core nodes
(comfy_extras/nodes_ace.py), not a third-party pack, and Comfy-Org's own
workflow_templates repo has an official ACE-Step-v1 template built from
those plus long-stable core nodes. tools/_comfyui/workflows/ace-step-1-t2a.json
was built by cross-checking every node's class_type and input names against
ComfyUI's own source (nodes_ace.py, nodes_audio.py, nodes_latent.py,
nodes.py) rather than trusting the UI-format export directly.
comfyui_music now defaults to this bundled workflow: prompt maps to
ACE-Step's tags field (matching suno_music's "prompt = music description"
convention), lyrics/duration_seconds/steps/cfg/lyrics_strength/seed are all
patchable, and missing ace_step_v1_3.5b.safetensors surfaces through the
same missing_models contract as image/video. workflow_json/workflow_path +
output_node remains available for ACE-Step 1.5, other node packs, or
different audio models entirely.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "music generation" open question from the adapter plan.
Unlike comfyui_image/comfyui_video there is no bundled workflow: ACE-Step's
ComfyUI node interface isn't standardized across custom node packs
(AceStepModelLoader vs native TextEncodeAceStepAudio, etc.), so instead of
picking one pack and breaking for everyone else, comfyui_music always
requires a caller-supplied workflow_json/workflow_path + output_node --
the same override contract image/video offer as an alternative, just
mandatory here. prompt is provenance-only, never injected into the graph.
Routed through the existing registry.get_by_capability("music_generation")
path alongside suno_music/music_gen -- no dedicated selector needed.
ComfyUIClient.generate() now also reads the "audio" output key (what
ComfyUI's native SaveAudio node writes), and gets timeout/resume/websocket-
wait/multi-server support for free via the shared client. Duration is a
best-effort ffprobe probe of the downloaded file since a custom workflow
gives no other way to know it ahead of time.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "multi-server" open question from the adapter plan.
ComfyUIClient(capability="image"|"video") now resolves its server URL
from COMFYUI_IMAGE_SERVER_URL / COMFYUI_VIDEO_SERVER_URL first, falling
back to the shared COMFYUI_SERVER_URL and then the localhost default —
so comfyui_image and comfyui_video can point at separate ComfyUI
instances (different GPUs, different model sets) with zero extra config
for single-server setups. is_default_url/unavailable_reason() and the
setup_offer metadata account for the override.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resolves the "async generation" open question from the adapter plan.
generate() now watches ComfyUI's websocket events (executing/progress/
execution_error) and reacts immediately instead of sleeping between REST
polls, with an optional on_progress callback that comfyui_video uses to
print step progress on long renders. websocket-client is an optional
import; _wait() falls back to the original poll() loop (with the
remaining time budget, not a fresh one) when it's unavailable or the
connection drops, so resume_prompt_id recovery is unaffected either way.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Non-accelerated local-GPU workflows (e.g. Wan 1.3B at 832x480/81-97
frames) routinely took ~1360-1630s, so the old 900s default false-failed
real renders that were still completing server-side. Timeout is now a
configurable timeout_seconds input (default 3600s), and ComfyUIError
carries the prompt_id on error/timeout so a timed-out-but-still-running
job can be resumed via resume_prompt_id instead of resubmitted.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The env var added complexity without meaningful benefit — explicit model
selection via the "model" input parameter is sufficient for both image and
video TokenHub tools.
- tools/video/hunyuan_cloud_video.py: drop env var fallback from
_resolve_model(), remove mention from install_instructions
- tests/contracts/test_hunyuan_cloud_video.py: remove
test_resolve_model_from_env and test_resolve_model_input_overrides_env
- .env.example: move TENCENT_TOKENHUB_API_KEY to a dedicated "Tencent
Hunyuan TokenHub API" section, drop TENCENT_TOKENHUB_MODEL comment,
broaden description from "video generation" to generic "Tencent Hunyuan
via TokenHub API"
Introduce a new video generation provider backed by the Tencent TokenHub
API (tokenhub.tencentmaas.com), an OpenAI-compatible gateway for Tencent
Hunyuan video models with simple Bearer-token auth.
- Add hunyuan_cloud_video tool (submit → poll → download) supporting
both text-to-video (hy-video-1.5) and image-to-video (yt-video-2.0)
- Add env vars: TENCENT_TOKENHUB_API_KEY, TENCENT_TOKENHUB_MODEL
- Add contract tests for the new tool
- Document setup, API flow, model pricing, and schema constraints in
PROVIDERS.md
- Update provider tables and capability matrix throughout docs
The greedy score mixed incommensurate scales: cosine similarity bounded
to [-1, 1] against an absolute list index that grows with the pool. For
a candidate j positions later to be preferred at the default
diversity=0.5, its similarity advantage had to exceed j -- impossible for
the non-negative cosines real footage embeddings produce. diversify()
therefore returned the input order verbatim, placing exact-duplicate
clips in adjacent edit slots, the one thing its docstring promises to
prevent. The threshold where the knob started working also depended on
pool size (0.66 at 4 candidates, 0.95 at 11).
Normalize the position term to [0, 1] so both terms share a scale. The
documented endpoints hold exactly as before: diversity=0 returns input
order, diversity=1 picks the most mutually dissimilar. Enumerating the
position also drops the O(n^2) remaining.index() lookup per candidate.
Closes#392
