Full BF16 version:
chroma1_radiance_x16_calibrated.safetensors
Chroma1-Radiance (calibrated)
A lightly-calibrated checkpoint of Chroma1-Radiance by @LodestoneRock.
All credit for the underlying model goes to lodestones โ please support their work at:
- Hugging Face: https://huggingface.co/lodestones/Chroma1-Radiance
- Ko-fi: https://ko-fi.com/lodestonerock
What this is
The objective was:
- Improve overall visual quality โ sharper details
- Reduce leftover stochastic noise โ the high-frequency speckle that occasionally survives the late denoising steps in pixel-space generation.
- Reduce visibility of 16-px patch grid artifacts โ the regular checkerboard pattern from Radiance's patch tokenizer, especially in flat regions.
Files
| File | Size | Format | Use |
|---|---|---|---|
chroma1_radiance_x16_calibrated.safetensors |
19 GB | BF16 | Full precision, drop-in replacement for the base safetensors |
chroma1_radiance_x16_calibrated_F16.gguf |
19 GB | F16 | Full precision, GGUF |
chroma1_radiance_x16_calibrated_Q8_0.gguf |
10.1 GB | GGUF Q8_0 | Use with city96/ComfyUI-GGUF, ~half size, near-lossless |
chroma1_radiance_x16_calibrated_Q5_1.gguf |
7.14 GB | GGUF Q5_1 | Smaller GGUF for tighter VRAM (~8 GB cards with offload) |
Pixel-space โ no VAE needed. Same workflow as vanilla Chroma1-Radiance.
Sample outputs
License
Inherits from Chroma1-Radiance โ Apache-2.0.
- Downloads last month
- 13
Hardware compatibility
Log In to add your hardware
5-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for wertz6969/chroma1_radiance_x16_calibrated
Base model
lodestones/Chroma1-Radiance
































