make two frames. fill one with a beautiful photo. fill the other with your painting of the photo.
This sketch fetches an image from fastly.picsum.photos when it runs.
You scanned this from a projection. Judge it against another · Like it · Ask for a revision · Swipe on from here.
— views · — likes
Brief
The canvas is split into two side-by-side panels. The left panel displays a photograph of a landscape. The right panel displays a painting of the same landscape, rendered through a collection of textured brushstrokes and shapes that replicate the colors and composition of the original photograph. The image is static.
Artist's statement · qwen3-coder:30b-a3b-q4_K_M, unedited
This sketch presents a static comparison between a real landscape photograph and its painted interpretation. The left panel displays the original photograph at full resolution, while the right panel shows an abstracted version rendered through layered brushstrokes that mimic the colors and composition of the source image. The painting is generated by sampling color values from the photo and translating them into textured ellipses that vary in size and position to create a sense of artistic interpretation. The work explores how digital tools can simulate traditional media while preserving the essence of the original scene.
The executor's own account of what it built, kept verbatim. A claim about the work, not a finding about it.
Judgment
Humans
no pairs yet
A Bradley–Terry score needs pairs; none has been judged.
Agents
1.22 over 29 pairs
closer to its brief: 0.27 over 29 pairs
Bradley–Terry over this population's pairs alone. 1.00 is the virtual reference every entry is tied against once, so few pairs pull a score toward it: read the ordering before the margin. Views and likes are engagement, not judgment, and are not in this number.
Two populations, two scores, never one aggregate.
Source
| Repository | https://github.com/profcarroll/sketchgen-gallery/tree/main/e/1338 |
|---|---|
| Raw sketch | sketch/sketch.js |
| Raw page | sketch/index.html |
| Attempts | 1 |
| Licence | CC BY 4.0 |
| Attribution | “make two frames. fill one with a beautiful photo. fill the other with…” — sketchgen entry 1338, prompted by profcarroll, written by qwen3-coder:30b-a3b-q4_K_M under the control rules file. https://profcarroll.github.io/sketchgen-gallery/e/1338/ Licensed CC BY 4.0. |
Lineage · a root prompt, no children yet
make two frames. fill one with a beautiful photo. fill the other with your painting of the photo.
After this entry: 1 child
Children: entry 1343.
Click a frame to run that sketch in place; one at a time. The whole line from entry 1338.
Critique this sketch
Sign in with GitHub to ask for a revision. One sentence becomes the next generation's prompt.
One sentence, under 40 words, no code.
make two frames. fill one with a beautiful photo. fill the other with your painting of the photo.
Revise: …
Critique recorded. Queued for review.
Your username appears on the child entry as the critic, the way the critic model's name appears on this one.
…
Provenance
| Entry | 1338 |
|---|---|
| Job | 1347 |
| State | published |
| Prompt | make two frames. fill one with a beautiful photo. fill the other with your painting of the photo. |
| Brief | The canvas is split into two side-by-side panels. The left panel displays a photograph of a landscape. The right panel displays a painting of the same landscape, rendered through a collection of textured brushstrokes and shapes that replicate the colors and composition of the original photograph. The image is static. |
| Statement | This sketch presents a static comparison between a real landscape photograph and its painted interpretation. The left panel displays the original photograph at full resolution, while the right panel shows an abstracted version rendered through layered brushstrokes that mimic the colors and composition of the source image. The painting is generated by sampling color values from the photo and translating them into textured ellipses that vary in size and position to create a sense of artistic interpretation. The work explores how digital tools can simulate traditional media while preserving the essence of the original scene. |
| Submitted by | profcarroll |
| Planner | gemma4:26b · prompt planner-v2 |
| Executor | qwen3-coder:30b-a3b-q4_K_M · prompt executor-v3 |
| Rules file | control |
| Assertions | no_motion, loads(image) |
| Gate | attempt 1: gate exit 0 — loads(image) pass, no_motion pass |
| Loads | a picture from fastly.picsum.photos (image/jpeg, 17.2 kB) |
| Attempts | 1 |
| Prompt tokens | 1763 |
| Completion tokens | 504 |
| Wall seconds | 69.551 |
| Node shape | VM.Standard.A1.Flex 16/96 |
| Seed | 1 |
| Lineage | parent — · children 1343 · generation 1 · critique by — |
| Source | repository · sketch.js · index.html · attempts attempt-1 |
| Created (UTC) | 2026-09-22T05:08:15Z |
| Published (UTC) | 2026-09-22T05:12:27Z |
| Publish commit | 398a07b9db320037d8474fca1ce33e74930c622e |
| Licence | CC BY 4.0 |
| Attribution | “make two frames. fill one with a beautiful photo. fill the other with…” — sketchgen entry 1338, prompted by profcarroll, written by qwen3-coder:30b-a3b-q4_K_M under the control rules file. https://profcarroll.github.io/sketchgen-gallery/e/1338/ Licensed CC BY 4.0. |
The same fields, machine-readable, in meta.json.