30f3d613e8
Both lanes were fully wired (workflow + custom node + OWUI lane) but their weights were never fetched by setup-ai-studio.sh -> download_studio_models.sh, so selecting either returned a cryptic "ComfyUI generation error" — the log shows FileNotFoundError: <model> is not installed (download_if_missing: false). - HiDream: download_hidream_o1.sh existed and is correct, but the roster never invoked it. Wire it in. - Chroma: had no downloader at all. Its UNET (Chroma1-HD-fp8mixed), the shared t5xxl_fp16 encoder, and the flux ae VAE relied on the legacy (now-unwired) download_models.sh already being on disk. Add download_chroma.sh (mirrors download_zimage.sh's split_files staging; ungated sources) and wire it in. - studio-models.tsv: add the chroma + hidream rows so c3's missing-model check, gpu-mode preflight, and the download modal know about them. Repo file paths verified against the live HF API. The downloads themselves are not run-verified here (no 120 GB pull); the script mirrors the proven sibling downloaders. test-studio-derig.sh green. Claude-Session: https://claude.ai/code/session_01EfF565T9eSLaqGzidyJ1Pm Co-authored-by: noonghunna <[email protected]> Co-authored-by: Claude Opus 4.8 <[email protected]>
28 lines
2.9 KiB
Plaintext
28 lines
2.9 KiB
Plaintext
# ai-studio model manifest — SINGLE SOURCE OF TRUTH for "what the ai-studio scene needs".
|
|
# Read by: c3 (services.py STUDIO_MODELS loader) · gpu-mode.sh (preflight_studio_models) ·
|
|
# the c3 download modal. Edit HERE only — every surface parses this file (no canary drift).
|
|
# Columns (TAB-separated): modality<TAB>label<TAB>root<TAB>rel_path<TAB>size_gb<TAB>installer
|
|
# modality : director | image | video | audio (director is the hard requirement; rest warn)
|
|
# root : weights (HF weights root, MODEL_DIR) | comfy (ComfyUI models tree, COMFYUI_MODELS_DIR)
|
|
# rel_path : the canary file under <root> whose presence == the model is installed
|
|
# installer: repo-relative download script (`bash <installer>`) that fetches it
|
|
# Roster note: bake-off done — Z-Image (image) + Wan2.2 (video) added as the uncensored picks.
|
|
# Krea 2: the earlier "cloud-only, DROPPED" verdict was PIN-specific. Native LOCAL Krea2 landed
|
|
# in ComfyUI v0.26.0 (#14589), so the weights are now a real studio model (download_krea.sh).
|
|
# The OWUI lane itself (workflow graph + studio_pipe entry) is wired at the on-rig validation
|
|
# that gates the v0.26.0 pin bump — until then this row tracks the weights only.
|
|
# See docs/ai-studio/image.md.
|
|
director Director (Qwen3.5-4B uncensored) weights qwen3.5-4b-gguf/hauhaucs-uncensored-q4km/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf 2.5 services/comfyui/download_director.sh
|
|
image Ideogram-4 (design / logo / text) comfy diffusion_models/ideogram4_fp8_scaled.safetensors 9.0 services/comfyui/download_ideogram4.sh
|
|
image Z-Image (uncensored / fast) comfy diffusion_models/z-image-turbo-fp8-e4m3fn.safetensors 6.15 services/comfyui/download_zimage.sh
|
|
image Krea 2 Turbo (aesthetic) comfy diffusion_models/krea2_turbo_fp8_scaled.safetensors 13.14 services/comfyui/download_krea.sh
|
|
image Chroma1-HD (uncensored) comfy diffusion_models/Chroma1-HD-fp8mixed.safetensors 9.0 services/comfyui/download_chroma.sh
|
|
image HiDream-O1 (top quality) comfy diffusion_models/HiDream-O1-Image-Dev-2604-FP8/model.safetensors 8.8 services/comfyui/download_hidream_o1.sh
|
|
video LTX-2.3 (video + audio) comfy unet/ltx2.3/distilled-1.1/ltx-2.3-22b-distilled-1.1-Q8_0.gguf 22.8 services/comfyui/download_video_models.sh
|
|
video Sulphur (uncensored video) comfy unet/sulphur-2/sulphur_dev-Q8_0.gguf 22.8 services/comfyui/download_video_models.sh
|
|
video 10Eros (uncensored video) comfy unet/10eros/10Eros_v1-Q8_0.gguf 22.8 services/comfyui/download_video_models.sh
|
|
video Wan2.2 (uncensored video) comfy unet/wan-rapid/Mega-v10/wan2.2-rapid-mega-aio-nsfw-v10-Q8_0.gguf 18.65 services/comfyui/download_wan.sh
|
|
audio ACE-Step (music) comfy checkpoints/ace-step-1.5/all_in_one/ace_step_v1_3.5b.safetensors 7.7 services/comfyui/download_ace_step.sh
|
|
audio Stable Audio (SFX) comfy checkpoints/stable-audio-open-1.0.safetensors 4.85 services/comfyui/download_stable_audio.sh
|
|
audio Kokoro (narration) comfy tts/kokoro/kokoro-v1.0.onnx 0.3 services/comfyui/download_kokoro.sh
|