4381 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
warby	487b3cd4e2	[ENV-1] Add plan and env example for Nano Banana API keys	2025-12-12 22:26:21 -06:00
warby	44e5c380ee	[ENV-6] Cleanup planning artifact - plan moved to PR description ... - Removed PLAN.md as per Director's 'Living Plan' Protocol (Strategy A) - Final plan state preserved in commit history and PR description	2025-12-12 22:11:23 -06:00
warby	a4c41a7bab	[ENV-5] Document RunPod env configuration for Nano Banana ... - Updated PLAN.md with RunPod specific configuration instructions - Confirmed RunPod uses template env vars (os.environ) - No code changes needed for RunPod compatibility (Nano Banana supports env vars natively)	2025-12-12 22:11:09 -06:00
warby	745fbb34f2	[ENV-4] Validate Nano Banana config - validates env wiring ... - Verified .env file loaded via 'docker compose config' - GOOGLE_API_KEY correctly passed to container environment - Runtime validation skipped due to local driver constraints (valid config confirmed) - Config flow: .env -> docker-compose -> container env -> Nano Banana node	2025-12-12 22:10:50 -06:00
User Name	adfff60437	[ENV-3] Ignore .env file, keep example tracked	2025-12-12 21:52:30 -06:00
User Name	b9db75631c	[ENV-2] Wire .env file into docker-compose for Nano Banana	2025-12-12 21:49:02 -06:00
User Name	a1cbb66083	[ENV-1] Add plan and env example for Nano Banana API keys	2025-12-12 21:48:51 -06:00
User Name	5c3408980a	[STEP-5] Finalize nano banana setup - ready for review ... - Installation validated: Node cloned, deps installed, UI visible - Node location: /home/warby/ComfyUI/custom_nodes/ComfyUI_Nano_Banana - Dependencies installed: python-dotenv, google-generativeai, google-genai, google-cloud-aiplatform - Nodes available: NanoBananaAIO, NanoBananaMultiTurnChat - API key configuration documented in commit messages - Troubleshooting: Manual pip install required (COMFY_AUTO_INSTALL=1 skipped on non-first run) - Design decisions documented: - Used git clone (comfy-node-install.sh not in container mount) - Manual dependency install required - Future: Track ComfyUI-Manager as git submodule following release tags - Ready for merge after acceptance testing	2025-12-12 21:07:27 -06:00
User Name	ef92024b55	[STEP-4] Validate nano banana node in UI - validates visibility ... - Nodes registered: NanoBananaAIO, NanoBananaMultiTurnChat - Node display names: 'Nano Banana AIO', 'Nano Banana Multi-Turn Chat' - Import successful: 2.9 seconds load time (no IMPORT FAILED) - API key config method: Environment variable via .env file - Config location: /app/ComfyUI/custom_nodes/ComfyUI_Nano_Banana/.env - Config steps: 1. Copy .env.api.template to .env in node directory 2. Set GOOGLE_API_KEY="your-api-key-here" 3. Alternative: Use Vertex AI with gcloud auth application-default login - Basic workflow test: Not attempted (requires API key) - Next: Final documentation commit	2025-12-12 21:07:23 -06:00
User Name	25b5a8d7e4	[STEP-3] Restart container for dependency installation - validates deps ... - Restarted comfy container to trigger COMFY_AUTO_INSTALL=1 - Initial restart: Node failed to import (missing google-genai dependencies) - Manually installed requirements.txt: python-dotenv, google-generativeai, google-genai, google-cloud-aiplatform - After dependency install and restart: Node loaded successfully - Import time: 2.9 seconds (no IMPORT FAILED message) - Container status: healthy - Next: UI validation checkpoint	2025-12-12 21:07:00 -06:00
User Name	9537b96121	[STEP-2] Install ComfyUI_Nano_Banana node - validates placement ... - Cloned ru4ls/ComfyUI_Nano_Banana to custom_nodes/ - Used git clone method (comfy-node-install.sh script not available in container mount) - Node location: /home/warby/ComfyUI/custom_nodes/ComfyUI_Nano_Banana - Requirements.txt present: yes - Next: Container restart to trigger COMFY_AUTO_INSTALL=1	2025-12-12 21:02:04 -06:00
User Name	1b6821edcf	[STEP-1] Setup nano banana install branch - validates baseline ... - Create feature branch for ComfyUI_Nano_Banana custom node installation - Design decision: Using comfy-node-install.sh script due to ComfyUI-Manager frozen mode - Future work: Track ComfyUI-Manager as git submodule following release tags - Target: ru4ls/ComfyUI_Nano_Banana	2025-12-12 20:58:33 -06:00
User Name	1d5b9bc4fa	Add Docker setup for ComfyUI with GitHub release tracking ... - Add Dockerfile with CUDA 12.6 and Python 3.12 base - Add docker-compose.yml with GPU support and volume mounts - Add docker-entrypoint.sh script with venv management and OTEL support - Add comfy-node-install.sh helper for custom node installation - Update .gitignore to exclude Docker-related artifacts - Entrypoint ensures frontend package matches requirements.txt version - Optional OTEL instrumentation when OTEL_EXPORTER_OTLP_ENDPOINT is set - Volume-mounted repo allows git checkout of release tags without rebuilds	2025-12-12 20:21:57 -06:00
User Name	2505cc4bc9	Add Docker-related files to .gitignore	2025-12-11 20:46:18 -06:00
comfyanonymous	338d9ae3bb	Make portable updater work with repos in unmerged state. (#11281)	2025-12-11 18:56:33 -05:00
comfyanonymous	eeb020b9b7	Better chroma radiance and other models vram estimation. (#11278)	2025-12-11 17:33:09 -05:00
comfyanonymous	ae65433a60	This only works on radiance. (#11277)	2025-12-11 17:15:00 -05:00
comfyanonymous	fdebe18296	Fix regular chroma radiance (#11276)	2025-12-11 17:09:35 -05:00
comfyanonymous	f8321eb57b	Adjust memory usage factor. (#11257)	2025-12-11 01:30:31 -05:00
Alexander Piskun	93948e3fc5	feat(api-nodes): enable Kling Omni O1 node (#11229)	2025-12-10 22:11:12 -08:00
Farshore	e711aaf1a7	Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae (#11199)	2025-12-10 22:02:26 -05:00
Johnpaul Chiwetelu	57ddb7fd13	Fix: filter hidden files from /internal/files endpoint (#11191)	2025-12-10 21:49:49 -05:00
comfyanonymous	17c92a9f28	Tweak Z Image memory estimation. (#11254)	2025-12-10 19:59:48 -05:00
Alexander Piskun	36357bbcc3	process the NodeV1 dict results correctly (#11237)	2025-12-10 11:55:09 -08:00
Benjamin Lu	f668c2e3c9	bump comfyui-frontend-package to 1.34.8 (#11220)	2025-12-09 22:27:07 -05:00
comfyanonymous	fc657f471a	ComfyUI version v0.4.0 ... From now on ComfyUI will do version numbers a bit differently, every stable off the master branch will increment the minor version. Anytime a fix needs to be backported onto a stable version the patch version will be incremented. Example: We release v0.6.0 off the master branch then a day later a bug is discovered and we decide to backport the fix onto the v0.6.0 stable, this will be done in a separate branch in the main repository and this new stable will be tagged v0.6.1	2025-12-09 18:26:49 -05:00
comfyanonymous	791e30ff50	Fix nan issue when quantizing fp16 tensor. (#11213)	2025-12-09 17:03:21 -05:00
Jukka Seppänen	e2a800e7ef	Fix for HunyuanVideo1.5 meanflow distil (#11212)	2025-12-09 16:59:16 -05:00
rattus	9d252f3b70	ops: delete dead code (#11204) ... This became dead code in https://github.com/comfyanonymous/ComfyUI/pull/11069	2025-12-09 00:55:13 -05:00
Lodestone	b9fb542703	add chroma-radiance-x0 mode (#11197)	2025-12-08 23:33:29 -05:00
Christian Byrne	cabc4d351f	bump comfyui-frontend-package to 1.33.13 (patch) (#11200)	2025-12-08 23:22:02 -05:00
rattus	e136b6dbb0	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) ... * make setattr safe for non existent attributes Handle the case where the attribute doesnt exist by returning a static sentinel (distinct from None). If the sentinel is passed in as the set value, del the attr. * Account for dequantization and type-casts in offload costs When measuring the cost of offload, identify weights that need a type change or dequantization and add the size of the conversion result to the offload cost. This is mutually exclusive with lowvram patches which already has a large conservative estimate and wont overlap the dequant cost so\ dont double count. * Set the compute type on CLIP MPs So that the loader can know the size of weights for dequant accounting.	2025-12-08 23:21:31 -05:00
comfyanonymous	d50f342c90	Fix potential issue. (#11201)	2025-12-08 23:20:04 -05:00
comfyanonymous	3b0368aa34	Fix regression. (#11194)	2025-12-08 17:38:36 -05:00
ComfyUI Wiki	935493f6c1	chore: update workflow templates to v0.7.54 (#11192)	2025-12-08 15:18:53 -05:00
rattus	60ee574748	retune lowVramPatch VRAM accounting (#11173) ... In the lowvram case, this now does its math in the model dtype in the post de-quantization domain. Account for that. The patching was also put back on the compute stream getting it off-peak so relax the MATH_FACTOR to only x2 so get out of the worst-case assumption of everything peaking at once.	2025-12-08 15:18:06 -05:00
dxqb	8e889c535d	Support "transformer." LoRA prefix for Z-Image (#11135)	2025-12-08 15:17:26 -05:00
Alexander Piskun	fd271dedfd	[API Nodes] add support for seedance-1-0-pro-fast model (#10947) ... * feat(api-nodes): add support for seedance-1-0-pro-fast model * feat(api-nodes): add support for seedream-4.5 model	2025-12-08 01:33:46 -08:00
Alexander Piskun	c3c6313fc7	Added "system_prompt" input to Gemini nodes (#11177)	2025-12-08 01:28:17 -08:00
Alexander Piskun	85c4b4ae26	chore: replace imports of deprecated V1 classes (#11127)	2025-12-08 01:27:02 -08:00
ComfyUI Wiki	058f084371	Update workflow templates to v0.7.51 (#11150) ... * chore: update workflow templates to v0.7.50 * Update template to 0.7.51	2025-12-08 01:22:51 -08:00
Alexander Piskun	ec7f65187d	chore(comfy_api): replace absolute imports with relative (#11145)	2025-12-08 01:21:41 -08:00
comfyanonymous	56fa7dbe38	Properly load the newbie diffusion model. (#11172) ... There is still one of the text encoders missing and I didn't actually test it.	2025-12-07 07:44:55 -05:00
comfyanonymous	329480da5a	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
rattus	4086acf3c2	Fix on-load VRAM OOM (#11144) ... slow down the CPU on model load to not run ahead. This fixes a VRAM on flux 2 load. I went to try and debug this with the memory trace pickles, which needs --disable-cuda-malloc which made the bug go away. So I tried this synchronize and it worked. The has some very complex interactions with the cuda malloc async and I dont have solid theory on this one yet. Still debugging but this gets us over the OOM for the moment.	2025-12-06 18:42:09 -05:00
comfyanonymous	50ca97e776	Speed up lora compute and lower memory usage by doing it in fp16. (#11161)	2025-12-06 18:36:20 -05:00
Jukka Seppänen	7ac7d69d94	Fix EmptyAudio node input types (#11149)	2025-12-06 10:09:44 -08:00
Alexander Piskun	76f18e955d	marked all Pika API nodes a deprecated (#11146)	2025-12-06 03:28:08 -08:00
comfyanonymous	d7a0aef650	Set OCL_SET_SVM_SIZE on AMD. (#11139)	2025-12-06 00:15:21 -05:00
Alexander Piskun	913f86b727	[V3] convert nodes_mask.py to V3 schema (#10669) ... * convert nodes_mask.py to V3 schema * set "Preview Mask" as display name for MaskPreview	2025-12-05 20:24:10 -08:00