Added FLUX VAE (ae.safetensors) to model configuration and updated
workflow to use it instead of non-existent pixel_space VAE.
This fixes the SaveImage data type error (1, 1, 16), |u1.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Both CLIP-L and T5-XXL come from the same repo, so they should
be in one entry with multiple files, not two separate entries.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add CLIP-L and T5-XXL entries with type: clip so they get
linked to /workspace/ComfyUI/models/clip/ directory for
FLUX model usage via DualCLIPLoader.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
FLUX models need to be in /workspace/ComfyUI/models/unet/ directory
for UNETLoader to find them, not in diffusion_models directory.
Changed type for:
- black-forest-labs/FLUX.1-schnell
- black-forest-labs/FLUX.1-dev
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add THUDM/CogVideoX-5b-I2V model entry (20GB, I2V-specific model)
- Add T5-XXL FP16 text encoder for CogVideoX (9GB)
- Add CLIP-L text encoder for CogVideoX and SD3 (1GB)
- Add CLIP-G text encoder for SD3 (3GB)
Note: CogVideoX models are auto-downloaded by DownloadAndLoadCogVideoModel node
Text encoders already linked manually to /workspace/ComfyUI/models/text_encoders/
- Change CLIP H from h94/IP-Adapter to openai/clip-vit-large-patch14
- Change CLIP G from h94/IP-Adapter to laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
- Update source paths to model.safetensors and open_clip_model.safetensors
- Fixes "header too large" error when loading CLIP vision models
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed CLIP Vision model source from openai/laion repos to h94/IP-Adapter
which provides the models in proper safetensors format that CLIPVisionLoader
can load directly.
Model sources:
- CLIP-ViT-H (SD 1.5): models/image_encoder/model.safetensors
- CLIP-ViT-bigG (SDXL): sdxl_models/image_encoder/model.safetensors
This fixes the "header too large" deserialization error caused by trying
to load PyTorch .bin files as safetensors.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
CLIPVisionLoader validates against a list of .safetensors files only.
Changed CLIP Vision model extensions from .bin back to .safetensors
in both the model configuration and workflow files.
Note: The actual files are PyTorch .bin format, but ComfyUI's
CLIPVisionLoader expects .safetensors naming convention. The symlinks
will point to the .bin files but use .safetensors extensions.
Changes:
- comfyui_models.yaml: Changed dest extensions to .safetensors
- Workflows: Changed clip_name to .safetensors extension
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed CLIP Vision model destination filenames from .safetensors to .bin
to match actual PyTorch model format. The files are ZIP/pickle format with
'PK' magic bytes, not safetensors format, which was causing "header too large"
deserialization errors in ComfyUI IPAdapterUnifiedLoader.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed destination filename to CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
to match the pattern expected by IPAdapterUnifiedLoader for SD1.5 models.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed CLIP-ViT-bigG destination filename to match the exact name
expected by IPAdapterUnifiedLoader: CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added two additional IP-Adapter variants:
- ip-adapter-plus_sdxl_vit-h.safetensors (0.9 GB) - High strength composition
- ip-adapter-plus-face_sdxl_vit-h.safetensors (0.5 GB) - Face-focused generation
These enable the PLUS and FACE presets in IPAdapterUnifiedLoader.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes:
- Added Stable Diffusion v1.5 model to comfyui_models.yaml
- Required for AnimateDiff motion modules (mm_sd_v15_v2.ckpt)
- Size: 4GB, VRAM: 8GB
- Updated AnimateDiff workflow to use SD 1.5 instead of SDXL
- Changed checkpoint from sd_xl_base_1.0.safetensors to v1-5-pruned-emaonly.safetensors
- Updated VRAM requirement from 18GB to 12GB
- Updated model requirements in metadata
AnimateDiff v15 motion modules are not compatible with SDXL.
This resolves: "Motion module 'mm_sd_v15_v2.ckpt' is intended for SD1.5 models"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed type fields to use actual ComfyUI directory names:
- diffusion_models → checkpoints (for FLUX, CogVideoX)
- musicgen → checkpoints (with notes about custom_nodes placement)
All models now properly map to real ComfyUI/models/* subdirectories.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
MusicGen Large is split into multiple files (pytorch_model-00001/00002-of-00002.bin)
Added all 3 files to the mapping (2 parts + index.json)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added 'files' array to all models specifying source and destination filenames
- Image models (FLUX, SDXL, SD 3.5): Use original checkpoint filenames
- Video models (CogVideoX, SVD): Use descriptive filenames
- Audio models (MusicGen): Prefix with model name for clarity
- Support models (CLIP, IP-Adapter, AnimateDiff): Keep original names
- This allows precise control over linked filenames in ComfyUI
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Audio model files (MusicGen) should not be mixed with image generation
checkpoints. Changed type from 'checkpoints' to 'audio_models' to ensure
they are linked to the correct ComfyUI directory.
- Add 'type' field to all model entries (diffusers, clip_vision, checkpoints, etc.)
- Add animatediff_models category with guoyww/animatediff repo
- Add ipadapter_models category with h94/IP-Adapter repo
- Map models to correct ComfyUI subdirectories
This fixes model linking issues where models weren't appearing in ComfyUI.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add arty.yml for repository management with environment profiles (prod/dev/minimal)
- Add CLAUDE.md with comprehensive architecture and usage documentation
- Add comfyui_models.yaml for ComfyUI model configuration
- Include deployment scripts for model linking and dependency installation
- Document all git repositories (ComfyUI + 10 custom nodes)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
