Chroma is a fantastic and highly versatile model. This finetune aims to improve reliability in realistic/photo-based styles while preserving Chroma’s broad concept knowledge. GGUFs on HuggingFace.
Prompting: Simple prompts describing what you want to see in natural language works well. Chroma prompts work well. Negative prompts don't work at CFG one. With CFG above one, negative prompts can be important. See the CivitAI page for example prompts.
Example settings (not necessarily optimal) using Comfy's default Chroma workflow:
Steps (base): ~30-40 (depends on other settings; CFG, sampler, etc.)
Steps (flash lora): 15-17 works well with rank-128/256. Depends on rank and settings.
CFG (base): ~3.5 (depends on other settings; steps, sampler, etc.)
CFG (flash lora): 1 works well with rank-128/256. Depends on rank and settings.
Sampler: My examples use res_2m or dpmpp_sde. res_multistep is also good
Scheduler: I like bong_tangent | beta & beta57 are also good
Support: Have too much money? Want to support further training? https://ko-fi.com/dawncreates
Training Details The model was trained locally, using Chroma-HD as the base. Each epoch included images at 3–5 different resolutions, though only a subset of the dataset was used per epoch. Except for the extra resolutions, OneTrainer's default config for 24gb Chroma finetuning was used. The dataset consists almost exclusively of SFW-images of people and landscapes, so to retain Chroma-HD's original conceptual understanding, several layers were merged back at various ratios. All the juice, compositions, subjects, and concepts come from Chroma itself, my model just nudges it towards realism. Honestly, this version is more of a showcase of how good Chroma is than a great finetune in itself. I do think it shows how much potential Chroma has for finetuning though - so get to work on Chroma finetuners - it has so much potential!
All images were captioned using JoyCaption: https://github.com/fpgaminer/joycaption
The model was trained using OneTrainer: https://github.com/Nerogar/OneTrainer