Sovereign 8s.is mirror of standardgalactic/steel-sky
  • Python 63.2%
  • HTML 25.6%
  • Shell 6.9%
  • Dockerfile 4.3%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
standardgalactic 25dac5c7d0 misc: Add steel-sky.txt (4180246 bytes)
Provenance: steel-sky
2026-10-03 17:01:47 -03:00
.devscripts v8 (#516) 2023-06-24 10:06:30 +02:00
.github Remove invoke (#705) 2024-06-23 11:16:21 +02:00
.vscode Force LF (#24) 2022-09-03 06:59:16 +02:00
catalogue catalogue: Add data entry 441 (graphic-treatment-assignments.csv) 2026-10-03 17:00:36 -03:00
data v8 (#516) 2023-06-24 10:06:30 +02:00
manifests manifests: Add data entry 70 (slate-samples.json) 2026-10-03 17:00:36 -03:00
projects project-03.01: Add markup line 9 (03.01-reconstruction-marker.svg) 2026-10-03 17:00:36 -03:00
services misc: Add line 21 (compose-snippet.yml) 2026-10-03 17:01:47 -03:00
thumbs samples: Add thumbs/old/sheets/sheet-31.webp (106102 bytes) 2026-10-03 17:01:40 -03:00
tools pipeline: Add line 13 (test-samples.sh) 2026-10-03 17:00:35 -03:00
.editorconfig Force LF (#24) 2022-09-03 06:59:16 +02:00
.gitattributes Force LF (#24) 2022-09-03 06:59:16 +02:00
.gitignore upstream-changes: Update upstream file .gitignore (155 bytes) 2026-10-03 17:00:35 -03:00
analyzing.txt misc: Add line 465 (analyzing.txt) 2026-10-03 17:01:44 -03:00
ankara-01.webp samples: Add ankara-01.webp (70958 bytes) 2026-10-03 17:00:36 -03:00
ankara-02.webp samples: Add ankara-02.webp (76622 bytes) 2026-10-03 17:00:36 -03:00
ankara-03.webp samples: Add ankara-03.webp (96546 bytes) 2026-10-03 17:00:36 -03:00
ankara-04.webp samples: Add ankara-04.webp (50866 bytes) 2026-10-03 17:00:36 -03:00
CLEANUP.md docs: Add text: If GitHub Pages serves index.html, check that it does not ... (CLEANUP.md) 2026-10-03 17:01:40 -03:00
commits-over-time.csv misc: Add data entry 216 (commits-over-time.csv) 2026-10-03 17:01:44 -03:00
CONTRIBUTORS.md docs: Add text: The upstream licence is kept unchanged in LICENSE. Its ter... (CONTRIBUTORS.md) 2026-10-03 17:01:40 -03:00
docker-compose.yml upstream-changes: Update upstream file docker-compose.yml (2194 bytes) 2026-10-03 17:00:35 -03:00
file-list.txt misc: Add lines 12196 to 12199 of file-list.txt (file-list.txt) 2026-10-03 17:01:47 -03:00
generate.py pipeline: Add code line 109 (generate.py) 2026-10-03 17:00:35 -03:00
generate_collection.py pipeline: Add code line 115 (generate_collection.py) 2026-10-03 17:00:35 -03:00
image-rater.html site: Add markup line 83 (image-rater.html) 2026-10-03 17:01:40 -03:00
image_descriptions.json site: Add image_descriptions.json (4115729 bytes) 2026-10-03 17:01:40 -03:00
index.html site: Add markup line 380 (index.html) 2026-10-03 17:01:40 -03:00
LICENSE [BREAKING] Rename UIs (#254) 2022-12-04 11:00:28 +01:00
prompts.txt misc: Add line 4 (prompts.txt) 2026-10-03 17:01:47 -03:00
provenance.csv docs: Add lines 12385 to 12386 of provenance.csv (provenance.csv) 2026-10-03 17:01:44 -03:00
PROVENANCE.md docs: Add text: The per-file table is in provenance.csv. (PROVENANCE.md) 2026-10-03 17:01:40 -03:00
README.md upstream-changes: Update upstream file README.md (17719 bytes) 2026-10-03 17:00:35 -03:00
results.json misc: Add data entry 1 (results.json) 2026-10-03 17:01:47 -03:00
steel-sky.txt misc: Add steel-sky.txt (4180246 bytes) 2026-10-03 17:01:47 -03:00
TODO.md docs: Add list item: [ ] Decide whether to keep image-rater.html or r (TODO.md) 2026-10-03 17:01:40 -03:00
workflow.json pipeline: Add data entry 374 (workflow.json) 2026-10-03 17:00:35 -03:00

Steel Sky

A working studio pipeline for a catalogue of 440 fiction screenplay projects and their graphic novel adaptations.

Based on AbdBarho/stable-diffusion-webui-docker. The Docker services, docker-compose.yml, LICENSE and the AUTOMATIC1111 and ComfyUI setup come from that project. Steel Sky adds the catalogue, the pilot projects, the manifest runner and the experiment site on top. For installation and troubleshooting, use the upstream wiki.

The repository holds three things:

  1. The catalogue. 440 screenplay projects in 22 cycles of 20, each illustrating a mathematical or conceptual framework.
  2. Pilot packages. A treatment, scene outline, screenplay and visual bible for each project on the first slate. Two are finished.
  3. The image pipeline. A local ComfyUI service driven by JSON manifests, used to test whether a small Stable Diffusion model can produce usable art for those visual bibles.

Earlier experiments in this repository (the Preliminary Run below, the image rater, and the large Blastoids, Macrolife and Aniara runs) are kept as an archive and described near the end.

Preliminary Run

The first test of the local pipeline, before the catalogue work began. Full-size files are in output/comfy locally.

Getting started

Requirements

  • Docker with Compose v2.
  • An NVIDIA GPU with the NVIDIA Container Toolkit, for the comfy profile. Without a GPU, use comfy-cpu instead, which is much slower.
  • Python 3.8 or newer on the host. The runner uses only the standard library. tools/make_thumbs.py needs pip install pillow.
  • About 10 GB of free disk for the images and model files.

Install

git clone https://github.com/standardgalactic/steel-sky
cd steel-sky

# 1. download the model files (first time only)
docker compose --profile download up --build

# 2. start ComfyUI
docker compose --profile comfy up --build

ComfyUI is then available at http://localhost:7860. Models are stored in data/models/, and generated images appear in output/comfy/. Stop it with Ctrl+C, or docker compose --profile comfy down from another terminal. The experiments use the Stable Diffusion 1.5 checkpoint v1-5-pruned-emaonly.ckpt, which the download profile fetches. Other profiles (auto, auto-cpu, comfy-cpu) and troubleshooting are covered in the upstream wiki.

Run an experiment

Keep ComfyUI running, and run the commands below from the repository root in another terminal. The runner expects generate.py and workflow.json in the working directory and talks to http://127.0.0.1:7860. Override these with --generator, --workflow and --url.

  1. Write a manifest. Copy manifests/slate-samples-v4.json, change name, and edit the categories and items. The format is described under "The image pipeline" below. Use a new name for each run so its images land in a separate folder.
  2. Check the prompts without generating:
    python generate_collection.py manifests/my-run.json --dry-run
    
    The first line gives the job count and total images, and each job shows the full prompt and negative prompt.
  3. Generate. Add --category 03.01 to run one project only, and repeat the flag for several:
    python generate_collection.py manifests/my-run.json --category 03.01
    
    Images are saved to output/comfy/my-run/<category>/<item>/.
  4. Resume or retry. Progress is saved in <manifest-name>.progress.json beside the manifest, and a re-run skips finished jobs. If a run was interrupted, the runner stops instead of risking a duplicate. Check the ComfyUI queue, then add --retry-incomplete to submit that job again. This may duplicate images.
  5. Build previews and view them:
    python tools/make_thumbs.py output/comfy --dst thumbs --size 512 --quality 80
    python -m http.server
    
    Open http://localhost:8000 to see the new run on the site. Commit thumbs/, not output/.

Practical limits: batch 4 at 512 x 512 fits modest GPUs, and lowering defaults.batch to 1 reduces memory use. A change to a shared prompt re-generates the affected jobs into the same folder.

Optional: the Arch tooling container

The Python tools can also run in an Arch Linux container, named after the archdaemon branch. ComfyUI stays in its own container. Add the arch service from services/arch/compose-snippet.yml to docker-compose.yml, start ComfyUI as above, then:

docker compose --profile arch up --build -d
docker compose exec arch bash

The project folder is mounted at /work, and the container runs as a user with your ids, so files it writes are yours. Reach ComfyUI at http://host.docker.internal:7860, which the container sets in $COMFY_URL:

python generate_collection.py manifests/my-run.json --url "$COMFY_URL"

Set PUID and PGID in the environment if your ids are not 1000. On Linux, host.docker.internal is provided by the extra_hosts line in the snippet. Stop it with docker compose --profile arch down.

1. The catalogue

catalogue/catalogue.md lists all 440 entries once each. Every entry has a title, a framework (mathematical, conceptual or both), a scale (S, M or L) and a graphic treatment note.

Count
Entries 440 (22 cycles of 20)
Scale S 194, M 230, L 16
Framework kind Mathematical 280, mixed 82, conceptual 78

Two audits keep the set varied:

  • catalogue/framework-family-audit.md assigns every entry to one of 26 framework families and enforces an 8 percent cap, which is at most 35 entries per family. The assignments are in framework-family-assignments.csv.
  • catalogue/graphic-treatment-audit.md checks that adaptation treatments are spread across the set. Assignments are in graphic-treatment-assignments.csv.

2. Pilot projects

The first slate is 01.01, 03.01, 04.01, 07.01, 08.01 and 11.01. Each pilot is developed in the same order: treatment, scene outline, screenplay, visual bible.

Slot Title Framework Status
03.01 The Last Projectionist Inverse problem: reconstructing a screening history from a missing reel Complete
01.01 The Department of Unclaimed Rooms Map versus territory, classification Complete
04.01 The Society for Perfect Endings Not started
07.01 Whale Beneath the Railway Not started
08.01 Seven Minutes of Summer Not started
11.01 A Country Made of Footnotes Not started

Files for finished pilots are in projects/03.01/ and projects/01.01/.

Expanding the catalogue

The catalogue is one file, catalogue/catalogue.md, with 22 cycle sections of 20 projects each. To add or change a project:

  1. Write the entry. Cycle 01 uses the full schema (title, cycle and slot, premise, framework, conditions, the protagonist's misunderstanding, graphic treatment, scale). Cycles 02 onward use the compact one-line format described under "Compact entry format" in the file. Copy a neighbouring entry in the same cycle and keep its layout.
  2. Keep the slot unique. Slots run CC.NN, for example 03.01, and each title appears once in the file.
  3. Respect the framework cap. No framework family may hold more than 8 percent of the catalogue, which is 35 of 440. The family of every entry is in catalogue/framework-family-assignments.csv. Add a row for a new entry and count the family before you commit. The reasoning is in framework-family-audit.md.
  4. Give it a graphic treatment and a row in graphic-treatment-assignments.csv, so the visual approaches stay spread across the set. See graphic-treatment-audit.md.
  5. Develop the project in four steps, in this order, one project at a time: treatment (with the ending resolved), scene outline, screenplay, visual bible. Save them in projects/<slot>/ with the slot first in the file name, for example 04.01-the-society-for-perfect-endings-treatment.md.
  6. Test its look. Add a category to a new manifest, put the visual bible's medium and light in the category prompt, and add the six standard items: palette-test, lead-character, main-location, key-object, core-device and page-layout. The findings above say which of those the generator can draw. Update the pilot table in this README when a project reaches a new stage.

The two audits were produced with one-off scripts that are not in this repository, so for now they are re-checked by counting the CSV rows.

3. The image pipeline

What it does

generate_collection.py reads a JSON manifest and submits each item to a local ComfyUI service through generate.py. A manifest holds a shared prompt, defaults, and categories, one per project, each with its own visual language and a list of items.

The prompt for each image is composed from the item prompt, then the category prompt, then the shared prompt. The negative prompt and seed come from the defaults. Per-item seeds are derived from the base seed and a hash of the output path, so a re-run reproduces the same images.

Manifest format

{
  "name": "slate-samples-v4",
  "shared_prompt": "graphic novel interior art, hand drawn, flat 2d illustration",
  "defaults": { "batch": 3, "variations": 1, "seed": 20261005, "negative": "text, watermark, photograph" },
  "categories": {
    "03.01": {
      "prompt": "charcoal drawing, heavy black shadows, worn film print texture",
      "items": [ { "name": "key-object", "prompt": "close up of a ribbon of film with small square holes along both edges" } ]
    }
  }
}

Manifest options and behaviour

  • Jobs. Each item gets variations separately seeded variants, and each variant is one job of batch images. With batch 3 and variations 2, an item makes 6 images in 2 jobs. Lower defaults.batch to 1 for less GPU memory, or defaults.variations to 1 for a smaller run.
  • Overrides. A category or an item can override the defaults with a settings object, for example "settings": {"batch": 2, "variations": 3, "seed": 42}. An item's negative adds exclusions to the inherited negative prompt. To replace the negative for a whole category, put it inside that category's settings.
  • Output names. ComfyUI saves images with prefixes such as slate-samples-v4/03-01/key-object/variant-001, so they appear under output/comfy/slate-samples-v4/. Change name to start a separate run folder.
  • Default manifest. With no manifest argument the runner reads collection.json, the original 32-item example kept from the earlier setup.
  • Progress file. <manifest-name>.progress.json records finished jobs. A re-run skips a job when its prompts, seeds, batch settings, workflow bytes and server URL all match. It does not check that the saved images still exist, so delete the matching entry (or the file) to regenerate. Do not run two copies against the same progress file at once.
  • Interrupted jobs. The runner stops rather than submit a possible duplicate. Check the ComfyUI queue and the output folder first, then use --retry-incomplete to submit that job again. This can duplicate images. If a job was accepted by the server but the client failed before recording it, reconcile it by hand or accept the duplicates.
  • Changing prompts. Changing the shared prompt regenerates the affected jobs into the same folders, and ComfyUI normally allocates new file names. Seeds are deterministic for each category, item and variant, but a different batch size or other settings can change the images.
  • Limits. A shared prompt gives visual coherence, not identical faces between scenes. Recurring identity needs a reference-image or character-conditioning workflow, which this setup does not have. Very long prompts can dilute specific details, so check a small category before a big run.
  • What the runner controls. Sampler, size, steps, CFG and checkpoint come from workflow.json. The runner supports the options of generate.py, and it does not do image-to-image or change the workflow.

Running it

See "Run an experiment" under Getting started. In short: write a manifest, check it with --dry-run, generate, then build thumbnails. Images are saved under output/comfy/<manifest-name>/<category>/<item>/. ComfyUI embeds the full prompt in every PNG, so any image can be traced back to its job from the file alone.

Setup used for the test

Stable Diffusion 1.5 (v1-5-pruned-emaonly.ckpt) in Docker, 512 x 512, 20 steps, CFG 8, Euler sampler, normal scheduler, denoise 1. No reference images and no LoRAs.

Findings from four runs (80 images)

Run Purpose Images
v1 First pass at six items per project 12
v2 Rewrote prompts to remove negation and abstract devices 24
v3 Full-bleed prompts, four seeds, no device items 32
v4 Targeted fixes for four weak items 12

What works with a model this size:

  • Medium and texture: charcoal with worn print grain, ink linework with flat wash.
  • Casting studies. Portraits are good but are not stable identities between seeds.
  • Locations and single props, when the prompt names a simple subject and a viewpoint.
  • A named film strip, as "a long thin ribbon of film with a row of small square holes along both edges".

What fails and is handled outside the generator:

  • Relational devices, such as a film frame growing out of a drawing or stacked tracing sheets in different inks. These are built as vector assets (projects/*/assets/).
  • Selective colour. Naming one object's colour sometimes works but cannot be held to that object.
  • Lettering, panel layouts and exact numbers. These are added in code after generation.
  • Anything stated as a negation in the positive prompt. The model draws the thing instead.

Practical prompt rules that came out of the test:

  • Put the subject and viewpoint first, the medium second.
  • Ask for "full bleed drawing that fills the entire image" and block frames, mats and gallery walls in the negative prompt, or the model draws a framed print.
  • Four seeds per portrait or location give a real choice. One seed does not.

Repository layout

catalogue/        the 440-entry catalogue, audits and assignment tables
projects/         pilot packages and their assets, one folder per slate project
manifests/        image manifests (slate-samples through v4)
tools/            make_thumbs.py and older helper scripts
thumbs/           compressed previews and prompt indexes (generated, committed)
samples/          selected full-quality picks (committed)
output/           raw ComfyUI output (not committed)
services/ data/   upstream Docker services and model folders

Previews and the archive

Raw output is not committed. Run

python tools/make_thumbs.py output/comfy output/old --dst thumbs

to build 192 px WebP previews, a index.jsonl of prompts and seeds for every image, and contact sheets of 400 images each. A thumbnail is about 3 KB, roughly 150 times smaller than the PNG it came from.

The archive in output/old holds about 12,000 images from earlier runs: Blastoids (5,100), ComfyUI test runs (4,100), Macrolife (1,000), Aniara (1,000), Steel-sky (887) and a small Political Art set, plus the curation and description tools that were used on them.

Upstream setup and features

This repository keeps the upstream services for two UIs:

For installation, GPU and model download instructions, see the upstream Setup and Usage wiki pages, and the FAQ if something goes wrong.

History and provenance

The first 237 commits are the upstream project's real history, with its real authors. The Steel Sky work was added on top of them from the finished files, one small step at a time, with tools/monotonic_commit.py. Those later commits carry real timestamps from the day they were made, so they describe how the files are built up, not when they were first written. Every file is classified against upstream in PROVENANCE.md and provenance.csv, and commits that touch an upstream file name its remaining authors in their trailers.

Contributing

Contributions are welcome. Open a discussion about the problem and the change you want to make before implementing anything.

Disclaimer and license

The authors are not responsible for content generated with this interface. The license inherited from upstream forbids sharing content that violates laws, causes harm to a person, discloses personal information meant for harm, spreads misinformation or targets vulnerable groups. See LICENSE for the full restrictions.

Thanks

See CONTRIBUTORS.md for the people whose commits make up the upstream project's history.

Steel Sky is based on AbdBarho/stable-diffusion-webui-docker, and thanks go to its maintainers. Thanks also to the projects that repository builds on: AUTOMATIC1111/stable-diffusion-webui, ComfyUI, CompVis/stable-diffusion, InvokeAI and Sygil-webui.