Default workflows to SDXL CyberRealistic; ship empty model preseed

Drops the SD 1.5 placeholder. The shipped txt2img/img2img workflows now
reference CyberRealisticXLPlay_V8.0_FP16.safetensors (the checkpoint
figment used in production), and comfyui-init-models.sh ships with no
active fetches — operators uncomment examples or add their own URLs.

The script + workflow filenames have to line up; README explains.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
57_WolveandClaude Opus 4.7 committed 2026-04-19 12:02:26 -05:00
1 parent 0ad99b6199
commit 704bcfdf13
4 files changed
+22 -14

No files matched your search

+13 -8
View File
@@ -63,9 +63,11 @@ Then edit:
Check sizes at <https://ollama.com/library> first; the host needs disk Check sizes at <https://ollama.com/library> first; the host needs disk
for everything listed. for everything listed.
- **`comfyui-init-models.sh`** — checkpoints/VAEs/LoRAs to preseed into - **`comfyui-init-models.sh`** — checkpoints/VAEs/LoRAs to preseed into
ComfyUI. Default ships SD 1.5 only (matches the workflow placeholder). ComfyUI. Ships empty (no active fetches) — uncomment the SDXL/Flux/
Uncomment the SDXL/Flux/upscaler examples or add your own. Set `HF_TOKEN` upscaler examples or add your own. Whatever filename you pick should
in `.env` if any are gated repos. match the `ckpt_name` field in `workflows/*.json` (default expects
`CyberRealisticXLPlay_V8.0_FP16.safetensors`). Set `HF_TOKEN` in
`.env` if any are gated repos.
## 3. Bring it up ## 3. Bring it up
@@ -91,10 +93,13 @@ ComfyUI ships no models. Three ways to get one in:
1. **Preseed via the sidecar (default).** `comfyui-model-init` runs once 1. **Preseed via the sidecar (default).** `comfyui-model-init` runs once
on `compose up`, downloads everything `comfyui-init-models.sh` lists, on `compose up`, downloads everything `comfyui-init-models.sh` lists,
and exits. The default list pulls SD 1.5 to match the workflow and exits. The script ships empty — uncomment one of the examples or
placeholder. Edit the script to add SDXL, Flux, LoRAs, upscalers, etc. add your own `fetch` calls (SDXL, Flux, LoRAs, upscalers, etc.). At
Re-run with `docker compose up -d comfyui-model-init` after edits; least one checkpoint should be named
already-present files are skipped. `CyberRealisticXLPlay_V8.0_FP16.safetensors` to match the workflow
default, or update `ckpt_name` in `workflows/*.json` to whatever you
pull. Re-run with `docker compose up -d comfyui-model-init` after
script edits; already-present files are skipped.
2. **ComfyUI-Manager UI.** Open `https://comfyui.example.com` (after 2. **ComfyUI-Manager UI.** Open `https://comfyui.example.com` (after
basic-auth login), click **Manager**, then **Model Manager**, install basic-auth login), click **Manager**, then **Model Manager**, install
from the catalogue. from the catalogue.
@@ -126,7 +131,7 @@ In Open WebUI: **Admin Panel -> Settings -> Images**.
4. **ComfyUI Workflow Nodes** -> paste the contents of 4. **ComfyUI Workflow Nodes** -> paste the contents of
[`../../workflows/txt2img.nodes.json`](../../workflows/txt2img.nodes.json). [`../../workflows/txt2img.nodes.json`](../../workflows/txt2img.nodes.json).
5. **Default Model** -> the filename of the checkpoint you dropped in 5. **Default Model** -> the filename of the checkpoint you dropped in
step 4 (e.g. `v1-5-pruned-emaonly.safetensors`). step 4 (e.g. `CyberRealisticXLPlay_V8.0_FP16.safetensors`).
6. Save. 6. Save.
For image editing (img2img), scroll to the **Image Editing** section in For image editing (img2img), scroll to the **Image Editing** section in
+7 -4
View File
@@ -39,10 +39,13 @@ fetch() {
# ─── Edit the list below to choose what gets preseeded ────────────────────── # ─── Edit the list below to choose what gets preseeded ──────────────────────
# Format: fetch <subdir under /models> <filename to save as> <direct URL> # Format: fetch <subdir under /models> <filename to save as> <direct URL>
#
# SD 1.5 base — matches the placeholder filename in workflows/*.json # No checkpoints are downloaded by default — the deployment ships expecting
fetch checkpoints v1-5-pruned-emaonly.safetensors \ # you to point at your own model mirror or the public examples below.
https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors # Whatever filename you pick should match the `ckpt_name` field in
# workflows/txt2img.json and workflows/img2img.json (the shipped default
# is CyberRealisticXLPlay_V8.0_FP16.safetensors); update either the
# script or the workflows so they line up.
# Examples — uncomment what you want. # Examples — uncomment what you want.
+1 -1
View File
@@ -17,7 +17,7 @@
"4": { "4": {
"class_type": "CheckpointLoaderSimple", "class_type": "CheckpointLoaderSimple",
"inputs": { "inputs": {
"ckpt_name": "v1-5-pruned-emaonly.safetensors" "ckpt_name": "CyberRealisticXLPlay_V8.0_FP16.safetensors"
} }
}, },
"6": { "6": {
+1 -1
View File
@@ -17,7 +17,7 @@
"4": { "4": {
"class_type": "CheckpointLoaderSimple", "class_type": "CheckpointLoaderSimple",
"inputs": { "inputs": {
"ckpt_name": "v1-5-pruned-emaonly.safetensors" "ckpt_name": "CyberRealisticXLPlay_V8.0_FP16.safetensors"
} }
}, },
"5": { "5": {