Mixed int8tensorwise + asymw4a8int8 (group 4, ConvRot-256) quant of 10ErosMaxFAST-H3refbeta6unstablepruned.safetensors, sized at 21.71GB to fit 24GB VRAM with headroom for VAE/text encoders. Load with stock ComfyUI UNETLoader, weightdtype=default. Testing-only release, same terms as source: do not merge, train on, or redistribute the file. Outputs and written opinions may be shared.
Independent publisher
Ac
cicalooo
Models in Library2
Datasets in Library0
Models on Hugging Face8
Followers47
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to image.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Learned INT8 ConvRot diffusion model for ComfyUI. Quantized from lodestones/Kroma (kroma-v0.3.1-turbo-opd). This model follows the Krea 2 Community License (krea-2-community-license), same as the source lodestones/Kroma / base Krea/Krea-2. Review the license terms before use or redistribution.