Spaces:
Runtime error
Runtime error
Commit History
-
fix(spaces): three runtime fixes — input staging dir, walker, cache perms
Unverified signature1. _COMFY_INPUT_DIR was hardcoded to <repo>/comfyui/input — fine locally but on Spaces ComfyUI lives at ~/comfyui, so user uploads were being staged to a directory ComfyUI never reads from. Mirror the bootstrap logic so the staging dir matches comfy_dir on each platform. 2. walk_workflow_for_models() was returning every filename mentioned in Power Lora Loader rows, including those with on:false. ensure_models then tried to download those (camera LoRAs) at runtime which failed noisily and pointlessly. Skip rows whose on flag is falsy. 3. After preload_from_hub bakes ~111 GB into ~/.cache/huggingface/, that directory tree's permissions can block runtime hf_hub_download writes (xet log dir, blob targets). chmod -R u+rwX in bootstrap so any model NOT covered by preload (the GGUF, conditional LoRAs) can still lazy-download. Failure to chmod is non-fatal.b348d5e
-
fix(models): walker recurses into Power Lora Loader nested dict + spatial upscaler comfy_type
Unverified signatureTwo issues surfaced when models actually downloaded but the workflow still failed at execution: 1. walk_workflow_for_models was a flat values() loop — Power Lora Loader stores rows as inputs.lora_1 = {on, lora, strength} (nested dict), so ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors was never returned to ensure_models. Recurse through dicts/lists. 2. ltx-2.3-spatial-upscaler-x2-1.0.safetensors was registered with comfy_type="upscale_models" but ComfyUI core's LatentUpscaleModelLoader reads from "latent_upscale_models" — same filesystem prefix, different folder. Fix the registry to match.8b4f49e -
fix(models): subfolder= on Kijai VAE/text-encoder entries
Unverified signatureKijai/LTX2.3_comfy keeps its files in vae/, text_encoders/, etc. The three entries missing subfolder= were 404ing on hf_hub_download. The exception fallback then rglobbed the cache and matched HF's .no_exist/ marker stubs — 0-byte files. Symlinking those to comfyui/models/vae/ left ComfyUI loading a 0-byte safetensors which crashes with "Error while deserializing header: header too small". Also harden the fallback to skip .no_exist/ paths and any file under 64 bytes so this class of stub-induced corruption can't recur.e168977 -
fix(models): walk_workflow_for_models reads API format
Unverified signatureThe walker was iterating workflow.get('nodes', []) which is editor format; our workflows are API format ({node_id: {class_type, inputs}}), so the walk returned an empty set, ensure_models was a no-op, and Spaces crashed at runtime with 'LTX23_audio_vae_bf16.safetensors not found'. Locally everything worked because the user's models are symlinked in. Also unstash the Sway Dance Lesson seed video — *.mp4 in .gitignore was silently excluding it from the deploy, so VHS_LoadVideo warned at submit time.84c4769 -
fix(spaces): use \$HOME instead of /data (no persistent-storage add-on needed)
Unverified signatureHF Pro grants ZeroGPU minutes but persistent storage at /data is a separate paid add-on. Without it /data is unwritable, which crashed the Space at startup. Switching the Spaces clone target and models dir to ~/comfyui — \$HOME is writable, and ZeroGPU containers freeze on sleep rather than tear down, so the clone effectively persists across calls within a single deploy.bc868d5 -
feat(spaces): registry entries for renamed BF16 aliases + seed inputs + bootstrap
Unverified signature- MODEL_REGISTRY: 6 new entries for the renamed-but-actually-BF16 files the master workflow references (gemma_3_12B_it_fp4_mixed → Comfy-Org/ltx-2, _transformer_only_fp8_scaled → Kijai _bf16, ltx-2-3-22b-dev-Q4_K_M.gguf → unsloth -BF16.gguf, taeltx2_3, distilled-lora-dynamic, gemma_3_12B_it). ModelEntry gets `source_filename` so the HF-side name and the workflow-expected name can differ. - ensure_models honors source_filename, joins subfolder into the HF path, and stages at comfyui/models/<comfy_type>/<workflow_filename>. - requirements.txt: add ComfyUI core deps + custom-node deps that are required for the LTX 2.3 workflow but aren't in their nodes' own requirements.txt (gguf, imageio_ffmpeg, opencv-python, matplotlib, diffusers, yt-dlp, psutil). - assets/seed_inputs/: tiny placeholder image/audio/video files that the bootstrap stages into comfyui/input/ so the workflow's always-on loaders don't fail on cold start when the user hasn't uploaded yet. - _bootstrap a…d35d872
-
fix(backend,models): runtime corrections from end-to-end testing
Unverified signature- backend: PromptExecutor needs (server, ...) not server_instance=None; init_extra_nodes is async — can't use asyncio.run() inside Gradio's event loop, run on a worker thread with a fresh loop instead; add minimal _StubServer with the surface PromptExecutor requires. - models: short-circuit ensure_models when the file already exists at comfyui/models/<type>/<file> — local dev path with user's existing ComfyUI models symlinked in shouldn't trigger HF Hub downloads.19489a8 -
ci: run unit tests + ruff lint on every push
Unverified signature3ea399a -
feat(models): ensure_models with HF cache symlinks + missing-file fallback
Unverified signature3d485ad -
feat(models): walk_workflow_for_models scans loader nodes
Unverified signature55a3bb4 -
feat(models): MODEL_REGISTRY mapping filenames to HF repos
Unverified signaturec80a8b9