Declared capabilities
- Cfgscale
- 3
- Local Checkpoint
- Chroma1-Base.safetensors
- Observed Resolution
- 1344x768
- Sampler
- dpmpp_2m
- Scheduler
- beta
- Steps
- 24
- Text to Image
- true
Model record · lodestones
Chroma1 Base
Generated locally through the SwarmUI JSON API at the operator-authorized 3090 Ti endpoint. No hosted inference provider or per-image API charge was used.
- Runs
- 3
- Policy
- local inference
- Version
- Chroma1-Base.safetensors
oss-r2-identity-chroma1-baseOss R2 Identity Chroma1 Base
Vision adherence score 3.5/10. Artifact-heavy natural owl on a small key-like prop rather than a large skeleton key; navy enamel and plausible exposed mechanics are absent; one eye is visibly amber, but the spectacles/fan/laboratory requirements fail and a tiny generated mark appears at lower right.
- Size
- 1344×768
- Seed
- not exposed
- Method
- local inference
oss-r2-spatial-chroma1-baseOss R2 Spatial Chroma1 Base
Vision adherence score 6.0/10. Nine objects: 3 red cubes, 2 glass spheres, 2 pyramid forms, and 2 crane-like paper forms. It gets the cube and sphere counts but duplicates both the pyramid and crane, and the pyramid is not directly behind the spheres.
- Size
- 1344×768
- Seed
- not exposed
- Method
- local inference
oss-r2-typography-chroma1-baseOss R2 Typography Chroma1 Base
Vision adherence score 4.0/10. Visible copy approximates 'MEASURE the MAGIC' but the lower ribbon contains malformed pseudo-text resembling 'ETI NOT LMARKETING'; line structure and exact-copy/no-extra-text constraints fail.
- Size
- 1344×768
- Seed
- not exposed
- Method
- local inference