From fd55ce666970419db830030f0545db7bdf11d756 Mon Sep 17 00:00:00 2001 From: Haylan Date: Thu, 24 Sep 2026 21:47:12 +0200 Subject: [PATCH] chore: remove image generation, Open WebUI, Lazytainer and neo4j Drops the comfyui, downloader-comfyui, open-webui, lazytainer and neo4j services with their volumes, env keys and update.sh steps, plus scripts/switch-model.sh and the two image-generation research docs. Refs #55 (removal inventory #58, intent vs. source #63) Co-Authored-By: Claude Opus 5.5 --- .env.example | 37 +-- docker-compose.yml | 185 +------------ .../research/image-generation-model-choice.md | 220 ---------------- docs/research/image-generation-options.md | 249 ------------------ scripts/switch-model.sh | 50 ---- scripts/update.sh | 2 - 6 files changed, 4 insertions(+), 739 deletions(-) delete mode 100644 docs/research/image-generation-model-choice.md delete mode 100644 docs/research/image-generation-options.md delete mode 100755 scripts/switch-model.sh diff --git a/.env.example b/.env.example index 6f2c87a..135f217 100644 --- a/.env.example +++ b/.env.example @@ -48,10 +48,6 @@ LLAMA_PARALLEL=2 # qwen-classifier service comment for the why and the VRAM/context math. LLAMA_CLASSIFIER_MODEL_FILE=Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf -# --- Lazytainer --- -# Seconds of inactivity before llama-server is stopped. 900 = 15 min. -LAZYTAINER_INACTIVE_TIMEOUT=900 - # --- SearXNG web search (see docs/research/litellm-searxng-search.md) --- # Resolved automatically by ./scripts/update.sh from search.home on this # host — leave blank. Only set by hand if that resolution fails (e.g. @@ -100,9 +96,9 @@ OMNIROUTE_WS_BRIDGE_SECRET= # Mint them by hand in the dashboard, add a KEY=value line here per workload # as you onboard one. See docs/proxy-key-onboarding.md. -# --- ComfyUI (local image generation, see issue #38 wayfinder map) --- -# Shared by every GPU-touching service (llama-server, llama-server-fast, -# comfyui) for group_add: — resolved to real host GIDs by ./scripts/update.sh +# --- GPU access (group_add GIDs) --- +# Shared by every GPU-touching service (llama-server, qwen-classifier) +# for group_add: — resolved to real host GIDs by ./scripts/update.sh # rather than left as plain group names in docker-compose.yml, because Docker # resolves a *named* group_add entry against the container's own /etc/group, # not the host's, and fails unpredictably when the image doesn't define one @@ -110,30 +106,3 @@ OMNIROUTE_WS_BRIDGE_SECRET= # docs/research/rocm-gpu-pin-and-render-group.md and issue #5). Leave blank. HOST_VIDEO_GID= HOST_RENDER_GID= - -# --- ComfyUI diffusion model (Qwen-Image 2.1, uncensored GGUF — see -# docs/research/image-generation-model-choice.md and issue #42) --- -# Three files, all from abenzerps/Qwen-Image-2.1-Uncensored-GGUF on -# HuggingFace: GGUF diffusion weights, safetensors text encoder, safetensors -# VAE. Q4_K_M is the repo's own recommended size/quality balance (~4.6GB); -# the int8 text encoder trades some quality for ~8GB less RAM than bf16. -# -# Requires the ComfyUI-GGUF custom node (github.com/city96/ComfyUI-GGUF) — -# NOT confirmed bundled in yurisasc/comfyui-rocm7.1. If the comfyui -# container doesn't show a "Unet Loader (GGUF)" node, `git clone` it into -# the image's custom_nodes dir and reinstall its requirements. -COMFYUI_DIFFUSION_MODEL_FILE=qwen-image-2.1-UC-Q4_K_M.gguf -COMFYUI_TEXT_ENCODER_FILE=qwen3vl_8b_int8_convrot.safetensors -COMFYUI_VAE_FILE=qwen_image_2.1_vae_bf16.safetensors - -# --- Open WebUI (chat + ComfyUI image-gen frontend) --- -# Chat backend goes through omniroute like every other client — mint this -# key by hand in the omniroute dashboard per docs/proxy-key-onboarding.md -# (label it openwebui-chat), no scripted mint yet. Image generation talks -# to comfyui directly, no key needed there. -OPENWEBUI_OMNIROUTE_KEY= - -# --- RAG databases (qdrant + neo4j, see wayfinder notes) --- -# No auth on qdrant (its default) — same trust boundary as llama-server: -# ai-stack is not exposed off-box. Random, filled in automatically: -NEO4J_PASSWORD= diff --git a/docker-compose.yml b/docker-compose.yml index a37c543..3847f26 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -47,13 +47,6 @@ services: - "8080" restart: unless-stopped networks: [ai-stack] - labels: - # ponytail: idle-timeout tuning lives here, not in a separate lazytainer config file — - # one place to look. Raise LAZYTAINER_INACTIVE_TIMEOUT if 15 min proves too eager. - - "lazytainer.group.llamaserver.sleepMethod=stop" - - "lazytainer.group.llamaserver.ports=8080" - - "lazytainer.group.llamaserver.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}" - - "lazytainer.group.llamaserver.minPacketThreshold=2" # Dedicated backend for qwen-code's tool-call harmfulness classifier # (fastModel in ~/.qwen/settings.json). Was aliased onto llama-server's own @@ -168,105 +161,6 @@ services: curl -L --fail --create-dirs -o /models/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf} https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/resolve/main/${LLAMA_CLASSIFIER_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf} - # Fetches the three Qwen-Image 2.1 (uncensored GGUF) files ComfyUI needs - # (diffusion model, text encoder, VAE) — same test -f guard pattern as - # downloader above. See docs/research/image-generation-model-choice.md and - # issue #42. - # - # GGUF weights go in models/unet (ComfyUI-GGUF's own convention), not - # models/diffusion_models (that was the old FP8-safetensors layout) — see - # github.com/city96/ComfyUI-GGUF. Text encoder/VAE stay safetensors, loaded - # by ComfyUI's normal CLIPLoader/VAELoader, so their folders are unchanged. - # - # ponytail: target paths otherwise assume ComfyUI's standard models/ layout - # under BASE_STORAGE_PATH (/storage) — same "not independently confirmed - # against the image's Dockerfile" caveat flagged on the comfyui service - # below. If ComfyUI doesn't pick these up, check its actual models root - # first. - downloader-comfyui: - image: curlimages/curl:latest - profiles: ["tools"] - user: root - volumes: - - comfyui-data:/storage - entrypoint: ["sh", "-c"] - command: - - > - mkdir -p /storage/models/unet /storage/models/text_encoders /storage/models/vae && - (test -f /storage/models/unet/${COMFYUI_DIFFUSION_MODEL_FILE:-qwen-image-2.1-UC-Q4_K_M.gguf} && - echo "diffusion model already downloaded, skipping" || - curl -L --fail --create-dirs -o /storage/models/unet/${COMFYUI_DIFFUSION_MODEL_FILE:-qwen-image-2.1-UC-Q4_K_M.gguf} - https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF/resolve/main/${COMFYUI_DIFFUSION_MODEL_FILE:-qwen-image-2.1-UC-Q4_K_M.gguf}) && - (test -f /storage/models/text_encoders/${COMFYUI_TEXT_ENCODER_FILE:-qwen3vl_8b_int8_convrot.safetensors} && - echo "text encoder already downloaded, skipping" || - curl -L --fail --create-dirs -o /storage/models/text_encoders/${COMFYUI_TEXT_ENCODER_FILE:-qwen3vl_8b_int8_convrot.safetensors} - https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF/resolve/main/text_encoders/${COMFYUI_TEXT_ENCODER_FILE:-qwen3vl_8b_int8_convrot.safetensors}) && - (test -f /storage/models/vae/${COMFYUI_VAE_FILE:-qwen_image_2.1_vae_bf16.safetensors} && - echo "vae already downloaded, skipping" || - curl -L --fail --create-dirs -o /storage/models/vae/${COMFYUI_VAE_FILE:-qwen_image_2.1_vae_bf16.safetensors} - https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF/resolve/main/vae/${COMFYUI_VAE_FILE:-qwen_image_2.1_vae_bf16.safetensors}) - - # Local image generation — see issue #38 (wayfinder map). yurisasc's image - # is gfx1201-tuned specifically (R9700's arch), unlike the official/AMD - # ComfyUI image which doesn't pin RDNA4 support — see - # docs/research/image-generation-options.md. - # - # Model is Qwen-Image 2.1 GGUF (uncensored variant, see .env.example) — - # needs the ComfyUI-GGUF custom node (github.com/city96/ComfyUI-GGUF) for - # its "Unet Loader (GGUF)" node. Not confirmed pre-installed in this image; - # if missing, exec in and `git clone` it into custom_nodes, then pip - # install its requirements.txt and restart the container. - comfyui: - image: yurisasc/comfyui-rocm7.1:latest - container_name: comfyui - devices: - - /dev/kfd - - /dev/dri - # Numeric GIDs, not names — see HOST_VIDEO_GID/HOST_RENDER_GID in - # .env.example and docs/research/rocm-gpu-pin-and-render-group.md. - group_add: - - "${HOST_VIDEO_GID:?run scripts/update.sh first to resolve this}" - - "${HOST_RENDER_GID:?run scripts/update.sh first to resolve this}" - security_opt: - - seccomp=unconfined - ipc: host - environment: - - HSA_OVERRIDE_GFX_VERSION=12.0.1 - - PYTORCH_ROCM_ARCH=gfx1201 - volumes: - - comfyui-data:/storage - # yurisasc/comfyui-rocm7.1 has no entrypoint/CMD of its own (just drops - # into bash) and doesn't read PUID/PGID/VIDEO_GID/RENDER_GID or - # BASE_STORAGE_PATH — confirmed by inspecting the image directly, so - # this command is required, not optional, or the container exits 0 - # immediately and restart-loops. Runs as root (image's only user); - # group_add above is what actually grants /dev/kfd + /dev/dri access. - # - # --base-directory fully replaces ComfyUI's custom_nodes/input/output/ - # user/temp dirs with ones under /storage (confirmed in folder_paths.py) - # rather than adding to the image's baked-in ones — so first boot must - # seed /storage/custom_nodes from the image's copy (ComfyUI-Manager - # lives there) or it's gone, and main.py hard-crashes if custom_nodes - # doesn't exist yet at all. - entrypoint: ["sh", "-c"] - command: - - > - mkdir -p /storage/custom_nodes /storage/input /storage/output /storage/user && - [ -z "$(ls -A /storage/custom_nodes)" ] && cp -r /workspace/ComfyUI/custom_nodes/. /storage/custom_nodes/ || true; - exec python main.py --listen 0.0.0.0 --port 8188 --base-directory /storage - # - # Published host port (unlike llama-server's ai-stack-only pattern): - # ComfyUI's own UI is meant to be reachable directly too, for a planned - # external nginx reverse-proxy route to comfy.home — not just through - # OmniRoute. Still also reachable at http://comfyui:8188 internally on - # ai-stack, which is the URL to register as OmniRoute's comfyui - # provider (dashboard or POST /api/providers, per docs/proxy-key-onboarding.md - # — same undocumented-in-repo manual flow already used for llama-server). - ports: - - "8138:8188" - restart: unless-stopped - networks: [ai-stack] - # Replaces litellm — see issue #31 (wayfinder map) for the full migration # rationale/findings. No static config.yaml equivalent: provider routing # (llama-server, searxng-search) is registered once through the dashboard @@ -349,28 +243,8 @@ services: retries: 3 start_period: 40s - lazytainer: - image: ghcr.io/vmorganp/lazytainer:master - container_name: lazytainer - # NOT network_mode: host — lazytainer identifies its own container by - # matching os.Hostname() against the Docker container-ID list - # (vmorganp/Lazytainer, configureFromLabels()); under host networking the - # container inherits the host's hostname instead of its own ID, so that - # match always fails and it panics with "Could not determine container ID - # of lazytainer" on every start. Host networking also can't see traffic - # to llama-server:8080 anyway — that port only exists on the ai-stack - # bridge network (no host port published, see issue #15 above). Joining - # ai-stack instead fixes both: hostname becomes the real container ID, - # and it's on the same network as the traffic it's watching. - networks: [ai-stack] - volumes: - - /var/run/docker.sock:/var/run/docker.sock:ro - restart: unless-stopped - depends_on: - - llama-server - # RAG vector store — see docs/agents/... (wayfinder). Dashboard UI published - # directly like comfyui above, not gatewayed through omniroute (it isn't an + # directly, not gatewayed through omniroute (it isn't an # LLM provider). qdrant: image: qdrant/qdrant:latest @@ -382,67 +256,10 @@ services: restart: unless-stopped networks: [ai-stack] - # RAG graph store, native vector index too (can absorb qdrant's job later - # if the two-DB split proves unnecessary — see wayfinder notes). - neo4j: - image: neo4j:5-community - container_name: neo4j - environment: - - NEO4J_AUTH=neo4j/${NEO4J_PASSWORD:?run scripts/update.sh first to resolve this} - volumes: - - neo4j-data:/data - ports: - - "7474:7474" # browser UI - - "7687:7687" # bolt - restart: unless-stopped - networks: [ai-stack] - - # Chat + image-generation frontend. Talks to ComfyUI directly for images — - # NOT through omniroute: OmniRoute's built-in `comfyui` provider hardcodes - # a CheckpointLoaderSimple (single-file-checkpoint) workflow in - # open-sse/handlers/imageGeneration/providers/comfyUI.ts with no override, - # so it can't drive Qwen-Image 2.1's split unet/text-encoder/vae GGUF - # loader chain. Open WebUI's ComfyUI backend is fully generic instead — - # you upload the exact workflow_api.json exported from ComfyUI's own - # graph editor and map arbitrary node IDs to parameters. - # - # Chat backend still goes through omniroute (OpenAI-compatible), same - # gateway every other client uses — mint OPENWEBUI_OMNIROUTE_KEY by hand - # per docs/proxy-key-onboarding.md, same as any other workload. - # - # ponytail: only wires the base ComfyUI URL + chat backend via env vars. - # COMFYUI_WORKFLOW/COMFYUI_WORKFLOW_NODES env vars exist but are reported - # flaky upstream — set the actual workflow JSON by hand in Settings > - # Images in the web UI instead, once you've exported it from ComfyUI. - open-webui: - image: ghcr.io/open-webui/open-webui:main - container_name: open-webui - depends_on: - comfyui: - condition: service_started - omniroute: - condition: service_started - environment: - - OPENAI_API_BASE_URL=http://omniroute:${OMNIROUTE_API_PORT:-20129}/v1 - - OPENAI_API_KEY=${OPENWEBUI_OMNIROUTE_KEY:-} - - ENABLE_IMAGE_GENERATION=True - - IMAGE_GENERATION_ENGINE=comfyui - - COMFYUI_BASE_URL=http://comfyui:8188 - - WEBUI_AUTH=True - volumes: - - open-webui-data:/app/backend/data - ports: - - "8008:8080" - restart: unless-stopped - networks: [ai-stack] - networks: ai-stack: volumes: models: omniroute-data: - comfyui-data: qdrant-data: - neo4j-data: - open-webui-data: diff --git a/docs/research/image-generation-model-choice.md b/docs/research/image-generation-model-choice.md deleted file mode 100644 index 30f858a..0000000 --- a/docs/research/image-generation-model-choice.md +++ /dev/null @@ -1,220 +0,0 @@ -# Research: which diffusion model to target with the full ~32GB R9700 - -**Question:** With Qwen/llama-server fully stopped (per issue #39's premise — see -map #38), ComfyUI has the whole ~32GB R9700 (ROCm/gfx1201) to itself instead -of the ~6GB left over during concurrent operation -(per [`image-generation-options.md`](image-generation-options.md)). Given that -headroom, should the build stay on FLUX.1-schnell, or move up to -FLUX.1-dev, SD3.5-large, Qwen-Image, HunyuanImage-3.0, or Krea-2? - -**Answer, short version:** move up to **Qwen-Image at FP8 precision** -(`qwen_image_fp8_e4m3fn.safetensors` diffusion weights + -`qwen_2.5_vl_7b_fp8_scaled.safetensors` text encoder, ~25GB combined). It's -the only one of the five upgrade candidates with **direct, hardware-specific -evidence of running on this exact GPU architecture** (gfx1201/R9700) rather -than a generic "ComfyUI supports ROCm" inference, it carries the cleanest -license of the group (Apache-2.0, no revenue threshold, no non-commercial -clause), and its 20B MMDiT is a real capability step up from schnell's -distilled 12B (notably for text rendering and prompt adherence), while still -fitting with real margin inside 32GB. - -## Why not just re-derive the schnell/dev/SDXL/SD3.5 findings - -`docs/research/image-generation-options.md` already covers, with primary -sources: ComfyUI's ROCm/gfx1201 story (official AMD docs + RDNA4 blog post + -community gfx1201 Docker images), FLUX.1-schnell vs FLUX.1-dev vs SDXL vs -SD3.5 licenses, and FLUX GGUF VRAM figures at the ~6GB-headroom scale. None -of that is repeated here except where the ~32GB ceiling changes the -conclusion. This doc adds: FLUX.1-dev/SD3.5 at the *larger* headroom, plus -three models the prior doc didn't cover at all (Qwen-Image, HunyuanImage-3.0, -Krea-2). - -## Candidate comparison - -| Model | License (primary source) | Params | Stated/typical VRAM | ROCm/gfx1201 evidence | -|---|---|---|---|---| -| FLUX.1-schnell (current) | Apache-2.0 | 12B | GGUF Q4_K_S ~7GB (per prior doc) | Confirmed on gfx1201 (prior doc) | -| **Qwen-Image** | **Apache-2.0** | 20B (20.4B DiT + 8.3B Qwen2.5-VL text encoder) | fp8 ~16GB (diffusion) + ~9.4GB (fp8 text encoder) ≈ 25GB total; bf16 needs 24GB+ and "48GB+" per some quant write-ups | **Direct**: [kyuz0/amd-r9700-comfy](https://github.com/kyuz0/amd-r9700-comfy) ships a pre-validated "Qwen Image 2512 (FP8) & Lightning LoRA (4 steps)" ComfyUI workflow specifically for the R9700 AI Pro (gfx1201), on a ROCm 7 (TheRock nightlies) toolbox | -| FLUX.1-dev | [FLUX.1-dev Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) — non-commercial weights, outputs usable commercially | 12B | bf16 ~24GB; GGUF Q8 ~12-13GB | Same *family* evidence as schnell (gfx1201 Docker images target FLUX generally), but no R9700-specific FLUX.1-dev report found | -| SD3.5-large | [Stability Community License](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md) — free under $1M annual revenue | 8B | bf16 ~16GB; 4-bit NF4 fits small GPUs | AMD's own ComfyUI-ROCm doc lists an "SD3.5 Simple" template workflow (per prior doc) — vendor-blessed but not R9700-specific | -| HunyuanImage-3.0 | [tencent-hunyuan-community license](https://github.com/Tencent-Hunyuan/HunyuanImage-3.0) | 80B total / 13B active (MoE, 64 experts) | Official repo: "≥ 3 × 80GB" VRAM for the base model, "≥ 8 × 80GB" for -Instruct; ~177GB at fp16 | **None, and actively contraindicated**: setup requires CUDA 12.8 + FlashAttention2/FlashInfer, no AMD/ROCm mention anywhere in the official repo | -| Krea-2 (Turbo) | [Krea 2 Community License](https://www.krea.ai/krea-2-licensing) — free under $1M annual revenue, homelab/personal explicitly covered | 12-13B DiT | No official VRAM figure; community reports (RTX hardware only) cite fp8 ~16GB, GGUF ~12GB | **None found** — released [June 22, 2026 per the HF model card](https://huggingface.co/krea/Krea-2-Turbo); ComfyUI added native support per [blog.comfy.org](https://blog.comfy.org/p/krea-2-open-source-models-are-now), and GGUF quants exist ([molbal/krea2-gguf](https://huggingface.co/molbal/krea2-gguf)), but no R9700/gfx1201-specific report exists yet — too new for that evidence to have accumulated | - -## Per-model detail - -### Qwen-Image — recommended - -- **License**: Apache-2.0, stated directly on the model card, no revenue - threshold, no non-commercial clause, no attribution/naming requirement. - The cleanest license of every model considered in this doc or the prior - one. Source: [Qwen/Qwen-Image on Hugging Face](https://huggingface.co/Qwen/Qwen-Image). -- **Architecture**: 20B-parameter MMDiT (Multimodal Diffusion Transformer) - combined with an 8.3B Qwen2.5-VL text encoder — notably larger and more - capable than FLUX.1-schnell's 12B distilled model, particularly for - multilingual text rendering and instruction-following, per the official - [QwenLM/Qwen-Image GitHub repo](https://github.com/QwenLM/Qwen-Image). -- **ComfyUI support**: native, not a wrapper/custom-node integration — - landed August 2025 per [ComfyUI Wiki's native-support announcement](https://comfyui-wiki.com/en/news/2025-08-05-qwen-image), - with an official FP8 checkpoint (`qwen_image_fp8_e4m3fn.safetensors`) and - FP8-scaled text encoder (`qwen_2.5_vl_7b_fp8_scaled.safetensors`, 9.38GB) - published under [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders). -- **VRAM at FP8**: the official Comfy-Org FP8 diffusion checkpoint plus FP8 - text encoder land around ~25GB combined — comfortably inside the 32GB - ceiling with headroom for ComfyUI runtime/VAE overhead, versus 24GB+ (some - sources say 48GB+) for the unquantized bf16 model. Sources: community - VRAM write-ups aggregated via [Comfy-Org/ComfyUI issue #10852 ("Qwen-image in 24GB VRAM and 32GB RAM")](https://github.com/Comfy-Org/ComfyUI/issues/10852) - and the [official ComfyUI Qwen-Image example](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/) — - treat exact GB figures as secondary/community-sourced, consistent with how - the prior doc flagged FLUX's GGUF VRAM table. -- **Direct R9700/gfx1201 evidence (the deciding factor)**: - [kyuz0/amd-r9700-comfy](https://github.com/kyuz0/amd-r9700-comfy) is a - Fedora-toolbox ROCm 7 (TheRock nightlies) environment built specifically - for the "AMD Radeon 9700 AI PRO (32GB)" and ships a pre-validated - "Qwen Image 2512 (FP8) & Lightning LoRA (4 steps)" ComfyUI workflow - (plus a Qwen-Image-Edit 2511 FP8 workflow) as one of only four workflows - in the whole repo. This is the only model in this comparison with - card-architecture-specific (not just "ComfyUI supports ROCm generically") - validation — everything else relies on family-level or vendor-generic - ROCm claims. A related community discussion - ([pollockjj/ComfyUI-MultiGPU #133](https://github.com/pollockjj/ComfyUI-MultiGPU/discussions/133)) - does flag that "Qwen image edit doesn't always work on AMD HIP/ROCm" in - some configurations — worth testing the specific workflow before assuming - zero friction, but this is a known-quantity, actively-discussed rough edge - rather than a documented hard blocker. -- **4-step Lightning LoRA**: the R9700-validated workflow pairs Qwen-Image - with a "Lightning" LoRA for 4-step inference — the same fast-inference - pattern FLUX.1-schnell uses, so switching models doesn't have to mean - giving up the short GPU-resident-time-per-image property the prior doc - called out as valuable for time-sliced use alongside llama-server (even - though this ticket's premise is llama-server being stopped, that pattern - still helps if the two services are ever run in an overlapping window). - -### FLUX.1-dev — solid alternative, not the pick - -- License permits non-commercial use of the weights; BFL's own license page - states generated outputs are separately usable commercially (already - covered in the prior doc; unchanged here). Source: - [FLUX.1-dev LICENSE.md](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). -- At bf16 (~24GB) or GGUF Q8 (~12-13GB), it fits the 32GB ceiling with room - to spare — a legitimate move up from schnell's distilled quality. - Source: [city96/FLUX.1-dev-gguf](https://huggingface.co/city96/FLUX.1-dev-gguf) - and community Q8 VRAM reports. -- Loses to Qwen-Image on two counts: license (non-commercial-weights clause - vs. Apache-2.0 — not a hard blocker for this homelab per the prior doc's - own reasoning, but strictly worse) and hardware evidence (FLUX's gfx1201 - validation is at the *family* level — the prior doc's `yurisasc/comfyui-rocm-rdna4` - and `charlie12345/R9700AIProComfyUIPatch` sources are about running FLUX - models on this card generally, not a FLUX.1-dev-specific report the way - kyuz0's repo is Qwen-Image-specific). - -### SD3.5-large — no longer the best use of the freed headroom - -- License unchanged from the prior doc: Stability Community License, free - under $1M annual revenue (irrelevant threshold for this homelab). Source: - [stabilityai/stable-diffusion-3.5-large LICENSE.md](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md). -- At 8B params (bf16 ~16GB), it's the smallest of the upgrade candidates — - which mattered when 6GB was the ceiling, but with 32GB available there's - no VRAM reason to pick the model the prior doc already flagged as "lower - fidelity than FLUX/SD3.5 by current standards" over Qwen-Image or - FLUX.1-dev. AMD's own ComfyUI-ROCm docs do list it as a first-party - example template ("SD3.5 Simple", per the prior doc), so it remains a fine - fallback if Qwen-Image's FP8 path hits the ROCm rough edge noted above. - -### HunyuanImage-3.0 — ruled out - -- Official repo states VRAM requirements of "≥ 3 × 80GB" for the base model - and "≥ 8 × 80GB" for HunyuanImage-3.0-Instruct — i.e. multi-GPU - datacenter-class NVIDIA clusters, not a single 32GB consumer/workstation - card at any precision. Source: - [Tencent-Hunyuan/HunyuanImage-3.0 GitHub repo](https://github.com/Tencent-Hunyuan/HunyuanImage-3.0). -- Setup instructions require CUDA 12.8, PyTorch 2.8.0 built for CUDA, and - optionally FlashAttention2/FlashInfer for MoE routing speed — no AMD or - ROCm path is mentioned anywhere in the official repo. Even the - MoE-efficient "13B active" framing doesn't help here: the tooling itself - assumes an NVIDIA multi-GPU cluster, and the 80B total parameter set still - has to be resident somewhere. -- 32GB of headroom on one AMD card doesn't move this model into reach at - any precision considered here; it's excluded regardless of how much VRAM - frees up on this specific box. - -### Krea-2 (Turbo) — promising, but unverified on this hardware - -- Verified directly against primary sources per the ticket's instruction - (this is a June 2026 release, past most training cutoffs): the - [Hugging Face model card](https://huggingface.co/krea/Krea-2-Turbo) states - a release date of **June 22, 2026**, a 12-billion-parameter single-stream - diffusion transformer, `torch.bfloat16` as the reference precision, and - the **Krea 2 Community License**. -- License, per [krea.ai/krea-2-licensing](https://www.krea.ai/krea-2-licensing): - non-commercial (including explicitly personal/homelab) use is free; - commercial use is permitted royalty-free for entities under $1M - trailing-12-month revenue (same shape as SD3.5's and matching this - homelab's use case); content-filter and AI-disclosure obligations apply if - deployed publicly; derivative model names must start with "Krea". -- ComfyUI added native support for both open-weight checkpoints (Krea 2 Raw - and Krea 2 Turbo) per [blog.comfy.org's announcement](https://blog.comfy.org/p/krea-2-open-source-models-are-now), - and community GGUF quants already exist - ([molbal/krea2-gguf](https://huggingface.co/molbal/krea2-gguf)), with - reports (RTX hardware only) of fp8 fitting 16GB and GGUF fitting 12GB. -- **No AMD/ROCm mention anywhere** in the model card, and no gfx1201/R9700 - community report was found — unsurprising given the model is roughly - 2.5 months old at the time of this research. Its architecture (a - standard-shaped DiT that ComfyUI loads through its normal diffusion-model - nodes, per the ComfyUI blog post) gives reasonable expectation it will run - on the same ROCm/PyTorch backend already proven for FLUX and Qwen-Image on - this card, but that's an inference, not a verified fact the way - kyuz0's Qwen-Image workflow is. -- **Not the pick today**, precisely because Qwen-Image already offers a - hardware-verified path at a comparable parameter count and VRAM budget. - Worth a follow-up research ticket once R9700/gfx1201-specific Krea-2 - reports exist — the license and ComfyUI support are both already in - place, so the only open question is real-world ROCm behavior. - -## Recommendation - -**Qwen-Image, FP8 precision** (`qwen_image_fp8_e4m3fn.safetensors` + -`qwen_2.5_vl_7b_fp8_scaled.safetensors`, ~25GB combined), optionally paired -with the 4-step Lightning LoRA the R9700-specific validated workflow uses. -It wins on all three axes the ticket asked about: - -1. **License**: Apache-2.0 — no restriction at all, strictly better than - every other candidate including the current FLUX.1-schnell pick. -2. **ROCm/gfx1201 compatibility**: the only candidate with a workflow - pre-validated specifically on this GPU architecture - ([kyuz0/amd-r9700-comfy](https://github.com/kyuz0/amd-r9700-comfy)), - not just "ComfyUI supports ROCm in general." -3. **VRAM at the ~32GB ceiling**: ~25GB at FP8 leaves real margin for - ComfyUI runtime/VAE overhead, without needing the multi-step, - non-distilled FLUX.1-dev's full 24GB bf16 footprint or accepting - SD3.5's lower fidelity ceiling — and it's a genuine capability upgrade - over schnell (20B vs. 12B, non-distilled-quality text rendering) rather - than just a bigger file. - -If the known Qwen-Image/ROCm edit-mode rough edge -([pollockjj/ComfyUI-MultiGPU #133](https://github.com/pollockjj/ComfyUI-MultiGPU/discussions/133)) -turns out to affect plain text-to-image generation too, SD3.5-large (AMD's -own first-party "SD3.5 Simple" ComfyUI-ROCm template workflow) is the -fallback, with FLUX.1-dev as a second option. HunyuanImage-3.0 is excluded -outright regardless of available VRAM (CUDA-only tooling, multi-GPU -datacenter VRAM floor). Krea-2 is worth revisiting once R9700-specific -field reports exist. - -## Sources consulted - -- [docs/research/image-generation-options.md](image-generation-options.md) (this repo — prior findings, not re-derived) -- [Qwen/Qwen-Image (Hugging Face)](https://huggingface.co/Qwen/Qwen-Image) -- [QwenLM/Qwen-Image (GitHub)](https://github.com/QwenLM/Qwen-Image) -- [ComfyUI Wiki — Qwen-Image native support announcement](https://comfyui-wiki.com/en/news/2025-08-05-qwen-image) -- [Comfy-Org/Qwen-Image_ComfyUI (Hugging Face, FP8 checkpoints)](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders) -- [Comfy-Org/ComfyUI issue #10852 — Qwen-Image VRAM](https://github.com/Comfy-Org/ComfyUI/issues/10852) -- [ComfyUI official Qwen-Image example](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/) -- [kyuz0/amd-r9700-comfy (R9700-specific ROCm ComfyUI toolbox)](https://github.com/kyuz0/amd-r9700-comfy) -- [pollockjj/ComfyUI-MultiGPU discussion #133 (Qwen-Image-Edit ROCm rough edge)](https://github.com/pollockjj/ComfyUI-MultiGPU/discussions/133) -- [black-forest-labs/FLUX.1-dev (Hugging Face) + LICENSE.md](https://huggingface.co/black-forest-labs/FLUX.1-dev) -- [city96/FLUX.1-dev-gguf](https://huggingface.co/city96/FLUX.1-dev-gguf) -- [stabilityai/stable-diffusion-3.5-large (Hugging Face) + LICENSE.md](https://huggingface.co/stabilityai/stable-diffusion-3.5-large) -- [Tencent-Hunyuan/HunyuanImage-3.0 (GitHub)](https://github.com/Tencent-Hunyuan/HunyuanImage-3.0) -- [krea/Krea-2-Turbo (Hugging Face)](https://huggingface.co/krea/Krea-2-Turbo) -- [Krea 2 Community License Agreement (krea.ai)](https://www.krea.ai/krea-2-licensing) -- [blog.comfy.org — Krea 2 open-source models in ComfyUI](https://blog.comfy.org/p/krea-2-open-source-models-are-now) -- [molbal/krea2-gguf (Hugging Face)](https://huggingface.co/molbal/krea2-gguf) diff --git a/docs/research/image-generation-options.md b/docs/research/image-generation-options.md deleted file mode 100644 index d1ba60c..0000000 --- a/docs/research/image-generation-options.md +++ /dev/null @@ -1,249 +0,0 @@ -# Research: adding local image generation to the stack - -**Question:** What's the best way to add local image generation alongside -the existing Qwen3.8-27B / llama.cpp text stack, given a single AMD Radeon -R9700 (32GB VRAM, ROCm/gfx1201 — not CUDA), routed through the OmniRoute -gateway on the `ai-stack` Docker network? - -**Answer, short version:** run **ComfyUI** (official AMD-blessed ROCm -Docker path exists, and OmniRoute already has a first-class `comfyui` -provider — no bespoke API wrapper needed) with **FLUX.1 [schnell]** -(Apache-2.0, 4-step, GGUF-quantizable) as the default model, falling back to -**SDXL** for anything schnell's distilled-step license/quality tradeoffs -don't suit. VRAM headroom against the current llama-server footprint is too -tight for both to be resident at once at any real image quality — plan for -**time-sliced use** (llama-server's existing lazytainer stop-on-idle pattern, -mirrored for the image-gen service, or a manual "stop one, start the other" -toggle), not concurrent operation. - -## Current VRAM baseline (from this repo) - -Per `docker-compose.yml` and `.env.example`, llama-server runs -`Qwen3.8-27B-UD-Q4_K_XL.gguf` (17.6 GB weights) at `--ctx-size 262144` with -`--cache-type-k q8_0 --cache-type-v q8_0`, landing at **~25.6 GB** total -(weights + q8_0 KV cache), leaving **~6 GB** free on the 32GB card — this -matches the math already recorded in -[`docs/research/qwen3.8-27b-quant.md`](qwen3.8-27b-quant.md). Per the auto-memory -note on this repo, real measured VRAM use has run closer to ~75% (~24 GB) in -practice versus the theoretical estimate, which doesn't change the -conclusion below but means the ~6 GB figure is closer to a ceiling than a -comfortable number. - -**Implication:** 6 GB is not enough for any current-generation image model at -usable quality (see VRAM table below — even the smallest practical FLUX -quant wants ~7 GB alone, before ComfyUI's own runtime/VAE overhead). Running -image-gen *concurrently* with llama-server resident is not realistic on this -card. The two need to time-share the GPU, not split it. - -## Backend evaluation (ROCm support, checked against primary sources) - -### ComfyUI — recommended - -- **Official AMD ROCm docs exist and are current.** AMD's own ROCm docs site - hosts a dedicated ComfyUI install guide with a prebuilt Docker image path - (recommended) or build-from-source, listing ROCm 7.2.0 and 7.1.0 as - supported versions, explicit `--device=/dev/kfd --device=/dev/dri - --group-add video` flags (same device-passthrough pattern this repo - already uses for llama-server), and template workflows including "SD3.5 - Simple". Officially the guide only names AMD Instinct - MI355X/MI325X/MI300X (datacenter cards) as supported platforms. - Source: [ROCm docs — ComfyUI on ROCm installation](https://rocm.docs.amd.com/projects/comfyui/en/docs-26.04/install/comfyui-install.html). -- **The upstream ComfyUI README itself documents AMD support directly**, - including consumer cards: stable ROCm install via - `pip install torch torchvision torchaudio --index-url - https://download.pytorch.org/whl/rocm7.2`, plus an experimental Windows - build explicitly naming **RDNA 3 (RX 7000), RDNA 3.5 (Strix Halo), and - RDNA 4 (RX 9000 series)** — i.e. the same RDNA4 generation as the R9700 — - and `HSA_OVERRIDE_GFX_VERSION` workarounds for older/unlisted cards. - Source: [comfyanonymous/ComfyUI README](https://github.com/comfyanonymous/ComfyUI). -- **AMD has published a specific RDNA4/RX 9000 ComfyUI guide** (separate - from the Instinct-only install page above), confirming RDNA4 consumer - cards are an explicitly supported, first-party-documented target, not just - a community workaround. - Source: [ROCm blog — Getting Started with ComfyUI on AMD Radeon RX 9000 Series GPUs](https://rocm.blogs.amd.com/artificial-intelligence/comfyui-radeon-9000/README.html). -- **gfx1201 (R9700's arch) specifically has active community Docker images**: - `yurisasc/comfyui-rocm-rdna4` targets ROCm 7.1 + PyTorch 2.9.1 with - `HSA_OVERRIDE_GFX_VERSION=12.0.1` / `PYTORCH_ROCM_ARCH=gfx1201` baked in, - and there's a published community patch specifically for R9700 AI Pro + - ComfyUI video-gen speedups, evidence the card is being run today, not just - theoretically compatible. - Sources: [yurisasc/comfyui-rocm-rdna4](https://github.com/yurisasc/comfyui-rocm-rdna4), - [charlie12345/R9700AIProComfyUIPatch](https://github.com/charlie12345/R9700AIProComfyUIPatch). -- **Known gfx1201 caveat:** AMD's own TransformerEngine repo has an open - issue confirming gfx1201 is missing from the FP8 architecture table, so - FP8 kernels silently fall back to FP32 with ~50% throughput loss - (18-22 vs. 35-40 tok/s in the reporter's LLM benchmark) — not a - correctness blocker, but relevant if planning to use FP8-quantized image - models expecting native FP8 speed on this card; GGUF/Q-quants (see below) - avoid this path entirely since they dequantize to bf16/fp16, not fp8. - Source: [ROCm/TransformerEngine issue #520](https://github.com/ROCm/TransformerEngine/issues/520). -- **Actively maintained community Docker packaging** beyond AMD's own image: - `YanWenKun/ComfyUI-Docker` ships parallel `rocm` (PyTorch-build-based, - faster releases) and `rocm7` (AMD-build-based, more comprehensive) - variants, both targeting ROCm 7, with ~1000 commits of ongoing history — - a viable alternative to the official AMD image if it lags behind ComfyUI - releases. - Source: [YanWenKun/ComfyUI-Docker](https://github.com/YanWenKun/ComfyUI-Docker). - -### AUTOMATIC1111 / Forge — usable but a step down for this hardware - -- ROCm support for A1111/Forge is real but community-patched, not - first-party. The upstream `lllyasviel/stable-diffusion-webui-forge` repo's - own discussion thread on AMD support points users to - `lshqqytiger/stable-diffusion-webui-amdgpu-forge`, a community fork - specifically maintained for AMD, "regarded as the go-to version" for - running FLUX-era models on AMD — i.e. the *mainline* Forge repo does not - claim ROCm support itself; you're expected to run a fork. - Source: [lllyasviel/stable-diffusion-webui-forge discussion #67](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/67). -- No first-party AMD vendor documentation (unlike ComfyUI's AMD-authored - ROCm/RDNA4 blog posts above) was found for A1111/Forge specifically. - Given ComfyUI already has an AMD-blessed path plus a first-class OmniRoute - provider (below), there's no reason to take on a community fork's - maintenance risk instead. - -### InvokeAI — usable but weaker AMD story for a new-generation card - -- InvokeAI documents ROCm support but flags it as second-tier: "AMD GPUs - are only supported on Linux," and "support for newer AMD GPUs is spotty - ... you may experience garbled images, black images, or long startup - delays." Its own install docs reference ROCm 5.4.2-era wheels, notably - older than the ROCm 7.x this stack's llama-server image already runs on - gfx1201. - Source: [InvokeAI installation docs (mauwii mirror)](https://mauwii.github.io/InvokeAI/installation/030_INSTALL_CUDA_AND_ROCM/). -- No OpenAI-compatible-images angle either — same drawback as A1111/Forge. - Not recommended as primary given ComfyUI's stronger, more current AMD - documentation trail. - -## Model choice: FLUX.1 [schnell] vs FLUX.1 [dev] vs SDXL vs SD3.5 - -| Model | License | Params | Notes | -|---|---|---|---| -| **FLUX.1 [schnell]** | **Apache-2.0** — fully open, no commercial restriction | 12B | Distilled for 1-4 step inference (fast); Black Forest Labs' own model card states this license directly | -| FLUX.1 [dev] | [FLUX.1-dev Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev) | 12B | Non-commercial for the *model/weights*; generated *outputs* are explicitly usable commercially per BFL's license page. Higher quality than schnell (more steps, non-distilled) but the weights themselves can't be redistributed/used commercially | -| SDXL | CreativeML OpenRAIL++ (permissive, commercial-friendly) | ~3.5B | Older (2023), lower fidelity than FLUX/SD3.5 by current standards, but lowest VRAM footprint and best long-standing tooling maturity | -| SD3.5 (Large/Medium) | Stability AI Community License — free commercial use under $1M annual revenue, else enterprise license required | 8B / 2.5B | Free for this repo's non-commercial homelab use regardless; template already listed in AMD's own ComfyUI-ROCm doc ("SD3.5 Simple") as a first-party example workflow | - -Sources: [black-forest-labs/flux model cards](https://github.com/black-forest-labs/flux/blob/main/model_cards/FLUX.1-dev.md), -[black-forest-labs/FLUX.1-schnell on Hugging Face](https://huggingface.co/black-forest-labs/FLUX.1-schnell) -(license: apache-2.0), [FLUX.1-dev LICENSE.md](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md), -[Stability AI — Introducing Stable Diffusion 3.5](https://stability.ai/news-updates/introducing-stable-diffusion-3-5), -[stabilityai/stable-diffusion-3.5-large LICENSE.md](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md). - -**Recommendation: FLUX.1 [schnell].** For a private homelab, license -enforcement isn't the deciding factor by itself, but schnell's Apache-2.0 -status removes any future ambiguity if outputs or the setup are ever shared -or repurposed, and its whole design point — good quality in 1-4 sampling -steps — directly addresses the VRAM/time-slicing constraint below (less -GPU-resident time per image than a 20-50 step dev/SDXL/SD3.5 run). -Quantized via `city96/ComfyUI-GGUF` (an actively-referenced, community- -trusted quantization node — its GGUF Q-quants dequantize to bf16/fp16 at -runtime, sidestepping the gfx1201 FP8 dequant bug above entirely), FLUX fits -in a fraction of its fp16 footprint: - -| Precision | Approx. VRAM (model only) | -|---|---| -| fp16 (baseline) | ~24 GB | -| fp8 | ~12 GB | -| GGUF Q5_K_S | ~12-15 GB (practical quality floor) | -| GGUF Q4_K_S | ~7 GB (quality starts degrading on hands/text below Q4) | - -Source: aggregated VRAM figures from GGUF-quantization write-ups referencing -city96's FLUX GGUF conversions — treat as secondary/community sourced -(no single BFL-published VRAM table was found), consistent across multiple -independent sources. -[city96/ComfyUI-GGUF README](https://github.com/city96/ComfyUI-GGUF/blob/main/README.md), -[city96/FLUX.1-dev-gguf model card](https://huggingface.co/city96/FLUX.1-dev-gguf). - -**Fallback pick: SDXL.** If schnell's distilled quality ceiling proves too -low for some use case, SDXL is the safer second choice over FLUX.1 [dev] or -SD3.5 specifically *because* of this card's tight headroom: it's the -smallest of the four by a wide margin, has the longest production track -record on ROCm of any of these models, and its OpenRAIL++ license carries no -revenue-threshold clause to track (unlike SD3.5's Community License) or -non-commercial weight restriction (unlike FLUX.1 [dev]). - -## OpenAI-compatible API / OmniRoute integration - -This is the best news in this research: **OmniRoute already ships a -first-class, built-in `comfyui` provider** — not a generic "point it at an -OpenAI base URL and hope" integration. Its provider reference documents it -explicitly: *"No API key required. Configure the local ComfyUI base URL -(default: http://localhost:8188)."* OmniRoute's own image-routing feature -set (`/v1/images/generations`, `/v1/images/edits`, `/v1/images/variations`, -with automatic provider fallback) is designed for exactly this pattern: -register ComfyUI as a backend, then any client already calling OmniRoute's -OpenAI-compatible images endpoints reaches it with no extra shim. -Source: [diegosouzapw/OmniRoute PROVIDER_REFERENCE.md](https://github.com/diegosouzapw/OmniRoute/blob/main/docs/reference/PROVIDER_REFERENCE.md), -[diegosouzapw/OmniRoute repo description](https://github.com/diegosouzapw/OmniRoute). - -This means **ComfyUI does not need an extra OpenAI-API wrapper project** — -the wrapper projects found during this research -([`ComfyUI-OpenAI-Compatible-API`](https://github.com/yeeyou/ComfyUI-OpenAI-Compatible-API)) -turned out to be a ComfyUI *custom node* for calling *outbound* to LLM APIs -from within a workflow (the reverse direction), not something this stack -needs — OmniRoute's own native ComfyUI provider is the actual integration -point, one layer up. - -**Confidence note:** the provider-reference detail above was fetched via an -automated summarizer against the raw doc rather than manually re-verified -line-by-line; re-check `PROVIDER_REFERENCE.md`'s `comfyui` entry directly -before wiring this up, in case ComfyUI's own `/prompt` API (a -workflow-graph-shaped API, not a simple text-prompt-in/image-out call) needs -a specific default workflow JSON configured on the OmniRoute side to produce -a plain text-to-image call. - -## Integration sketch (not a full compose — see caveats above) - -- New service in `docker-compose.yml`, e.g. `comfyui`, image - `rocm/comfyui-rocm` (or `yurisasc/comfyui-rocm-rdna4` for a gfx1201-tuned - build) or built from AMD's own ROCm ComfyUI Dockerfile, same - `/dev/kfd` + `/dev/dri` + `group_add: [video, render]` device-passthrough - block already used for `llama-server`, joined to the same `ai-stack` - network so `omniroute` can reach it as `http://comfyui:8188` — no host - port needed (matches the existing llama-server pattern of no published - port, gateway-only access). -- Register it in OmniRoute's dashboard as a `comfyui` provider pointing at - that internal URL, same manual-registration pattern already used for - llama-server and searxng-search per `docs/proxy-key-onboarding.md`. -- **VRAM contention is the real design problem, not networking.** Given the - ~6 GB headroom, the two services can't both sit GPU-resident. - Two workable patterns, in order of how well they fit what's already in - this repo: - 1. **Mirror the existing lazytainer stop-on-idle pattern** already applied - to `llama-server` (`docker-compose.yml`'s `lazytainer.group.*` labels) — - add an equivalent idle-timeout group for `comfyui`, and rely on the two - services naturally not being hit at the same time for a single-user - homelab. This doesn't *guarantee* mutual exclusion (both could still be - woken concurrently and both try to fit in 6 GB free), so it's a - reasonable-effort fit, not a hard guarantee. - 2. **Explicit mutual exclusion**: a small script/compose profile that - stops `llama-server` before starting `comfyui` (and vice versa) rather - than relying on lazytainer's independent idle timers — worth doing if - the reasonable-effort version above causes a visible OOM in practice. - Either way, this is a "pick one, then the other" story, not "run both." -- Given FLUX.1 [schnell]'s 1-4 step design, a cold-start-and-generate cycle - (wake ComfyUI from lazytainer sleep, generate, let it idle back down) is - a reasonably good fit for occasional image requests through the same - gateway that already does this for llama-server. - -## Sources consulted - -- [ROCm docs — ComfyUI on ROCm installation](https://rocm.docs.amd.com/projects/comfyui/en/docs-26.04/install/comfyui-install.html) -- [ROCm blog — ComfyUI on AMD Radeon RX 9000 Series (RDNA4)](https://rocm.blogs.amd.com/artificial-intelligence/comfyui-radeon-9000/README.html) -- [comfyanonymous/ComfyUI README](https://github.com/comfyanonymous/ComfyUI) -- [YanWenKun/ComfyUI-Docker](https://github.com/YanWenKun/ComfyUI-Docker) -- [yurisasc/comfyui-rocm-rdna4](https://github.com/yurisasc/comfyui-rocm-rdna4) -- [charlie12345/R9700AIProComfyUIPatch](https://github.com/charlie12345/R9700AIProComfyUIPatch) -- [ROCm/TransformerEngine issue #520 (gfx1201 FP8 fallback)](https://github.com/ROCm/TransformerEngine/issues/520) -- [lllyasviel/stable-diffusion-webui-forge discussion #67 (AMD support)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/67) -- [InvokeAI CUDA/ROCm install docs](https://mauwii.github.io/InvokeAI/installation/030_INSTALL_CUDA_AND_ROCM/) -- [black-forest-labs/flux GitHub repo + model cards](https://github.com/black-forest-labs/flux) -- [black-forest-labs/FLUX.1-schnell (Hugging Face, Apache-2.0)](https://huggingface.co/black-forest-labs/FLUX.1-schnell) -- [black-forest-labs/FLUX.1-dev LICENSE.md](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) -- [Stability AI — Introducing Stable Diffusion 3.5](https://stability.ai/news-updates/introducing-stable-diffusion-3-5) -- [stabilityai/stable-diffusion-3.5-large LICENSE.md](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md) -- [city96/ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) -- [city96/FLUX.1-dev-gguf](https://huggingface.co/city96/FLUX.1-dev-gguf) -- [diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute) and its `PROVIDER_REFERENCE.md` -- [yeeyou/ComfyUI-OpenAI-Compatible-API](https://github.com/yeeyou/ComfyUI-OpenAI-Compatible-API) (checked and ruled out — wrong direction) -- This repo: `docker-compose.yml`, `.env.example`, `docs/research/qwen3.8-27b-quant.md` diff --git a/scripts/switch-model.sh b/scripts/switch-model.sh deleted file mode 100755 index 1b7f1b1..0000000 --- a/scripts/switch-model.sh +++ /dev/null @@ -1,50 +0,0 @@ -#!/usr/bin/env bash -# Swap GPU residency between llama-server (Qwen) and comfyui — they never -# run concurrently, VRAM doesn't fit both (see issue #38's map). Manual -# invocation only, no auto-switching. -# -# Bypasses lazytainer entirely and drives docker compose directly — its -# idle-stop can't be used for this. Root cause (see -# docs/research/lazytainer-omniroute-idle-stop.md, issue #40): lazytainer's -# packet-threshold detector is source-blind and can't tell OmniRoute's -# periodic health-check pings apart from real traffic on the same port, so -# it never reliably sleeps a service on its own. A scripted swap always -# knows which service should go up/down, so it doesn't need that heuristic. -# -# OmniRoute may show the just-stopped provider as errored/offline in its -# dashboard for up to CREDENTIAL_HEALTH_CHECK_INTERVAL (default 5 min) after -# a swap — cosmetic, not a functional problem (see the research doc above). -set -euo pipefail -cd "$(dirname "$0")/.." - -usage() { - echo "Usage: $0 {qwen|comfyui}" >&2 - echo " qwen - stop comfyui, start llama-server" >&2 - echo " comfyui - stop llama-server, start comfyui" >&2 - exit 1 -} - -[ $# -eq 1 ] || usage - -case "$1" in - qwen) - from=comfyui - to=llama-server - ;; - comfyui) - from=llama-server - to=comfyui - ;; - *) - usage - ;; -esac - -echo "==> stopping $from" -docker compose stop "$from" - -echo "==> starting $to" -docker compose up -d "$to" - -echo "==> status" -docker compose ps diff --git a/scripts/update.sh b/scripts/update.sh index fad63af..1c5169b 100755 --- a/scripts/update.sh +++ b/scripts/update.sh @@ -183,7 +183,6 @@ set_if_blank OMNIROUTE_STORAGE_ENCRYPTION_KEY "$(openssl rand -hex 32)" set_if_blank OMNIROUTE_MACHINE_ID_SALT "$(openssl rand -hex 16)" set_if_blank OMNIROUTE_CLI_SALT "$(openssl rand -hex 16)" set_if_blank OMNIROUTE_WS_BRIDGE_SECRET "$(openssl rand -hex 32)" -set_if_blank NEO4J_PASSWORD "$(openssl rand -hex 16)" echo "==> resolving SEARXNG_LAN_IP" # search.home is a LAN mDNS/local-DNS name — resolvable from this host, just @@ -227,7 +226,6 @@ docker compose build --pull echo "==> ensuring models are downloaded (skips already-present files)" docker compose --profile tools run --rm downloader docker compose --profile tools run --rm downloader-classifier -docker compose --profile tools run --rm downloader-comfyui echo "==> bringing up omniroute" docker compose up -d --wait omniroute