All The LoRA FLUX Training Experiments I Have Done So Far (Patreon)
Content
I have been using a machine on RunPod that has 8x RTX A6000 over a week now. I have done all the following experiments with each one being 3000 steps.
I will hopefully update this post as I do more.
All findings, grids, and best configs and 1-click installers for Windows, RunPod and Massed Compute shared here : https://www.patreon.com/posts/kohya-flux-lora-110293257
You can see saved safetensors files in below repos. Click load more button at the end to see entire repo files
https://huggingface.co/MonsterMMORPG/FLUX_Kohya_SS_Massive_Research/tree/main
https://huggingface.co/MonsterMMORPG/FLUX_Kohya_SS_Massive_Research_Part2/tree/main
https://huggingface.co/MonsterMMORPG/FLUX_Kohya_SS_Massive_Research_Part3/tree/main
https://huggingface.co/MonsterMMORPG/FLUX_Kohya_SS_Massive_Research_Part4/tree/main
All Tested Experiments List So Far
1) 16GB_Config.safetensors
2) 1e_04_bf16_128_rank-000170.safetensors
3) 1e_04_bf16_128_rank_full_bf16.safetensors
4) 1e_04_fp16_128_rank-000180.safetensors
5) 1e_04_fp16_128_rank_full_fp16-000180.safetensors
6) 1e_04_fp8_32_rank-000170.safetensors
7) 1e_04_fp8_bf16_accelerate_32_rank-000160.safetensors
8) 1e_04_fp8_bf16_accelerate_full_bf16_32_rank-000160.safetensors
9) 1e_04_fp8_full_fp16_32_rank-000170.safetensors
10) 2e_04_fp8_bf16_accelerate_full_bf16_32_rank.safetensors
11) 3e_04_fp8_bf16_accelerate_full_bf16_32_rank.safetensors
12) 6e_05_best_additive_sigma.safetensors
13) 6e_05_best_additive_uniform.safetensors
14) 6e_05_best_max_grad_norm_0.safetensors
15) 6e_05_best_raw_sigma.safetensors
16) 6e_05_best_raw_sigmoid.safetensors
17) 6e_05_best_sigma_scaled_sigma.safetensors
18) 6e_05_best_with_reg_images.safetensors
19) 6e_05_bf16_128_rank_full_bf16.safetensors
20) 7e_05_bf16_128_rank_full_bf16.safetensors
21) 8e_05_bf16_128_rank_full_bf16.safetensors
22) 8e_05_fp8_bf16_accelerate_full_bf16_32_rank.safetensors
23) 9e_05_bf16_128_rank_full_bf16.safetensors
24) 9e_05_fp8_bf16_accelerate_full_bf16_32_rank.safetensors
25) Best_v1.safetensors
26) Best_v1_3e_5.safetensors
27) Best_v1_4e_5.safetensors
28) Best_v1_512px.safetensors
29) Best_v1_512px_Lowest_VRAM.safetensors
30) Best_v1_5e_5.safetensors
31) Best_v1_5e_5_max_grad_norm_0.safetensors
32) Best_v1_Lowest_VRAM.safetensors
33) Best_v1_T5_attention_mask.safetensors
34) Best_v1_cfg_3_5.safetensors
35) Best_v1_max_grad_norm_0.safetensors
36) Best_v1_reg_0_1_percent.safetensors
37) Best_v1_reg_prior_lost_0_3.safetensors
38) Best_v1_reg_prior_lost_0_6.safetensors
39) Best_v1_reg_prior_lost_1_0_apply_t5_attention_mask.safetensors
40) Best_v2.safetensors
41) Best_v2_1280.safetensors
42) Best_v2_1280_256rank.safetensors
43) Best_v2_1536.safetensors
44) Best_v2_1536_256rank.safetensors
45) Best_v2_FP8.safetensors
46) Best_v2_FP8_LowVRAM.safetensors
47) Best_v2_Rank16.safetensors
48) Best_v2_Rank256.safetensors
49) Best_v2_Rank32.safetensors
50) Best_v2_Rank4.safetensors
51) Best_v2_Rank64.safetensors
52) Best_v2_Rank8.safetensors
53) Best_v2_Split_QKV.safetensors
54) Best_v2_joycaption.safetensors
55) Best_v2_joycaption_Split_QKV.safetensors
56) CivitAI_FLUX.safetensors
57) Best_v2_shift_6e_05
58) Best_v2_shift_4e_05
59) Best_v2_shift_3e_05
60) Best_v2_shift_2e_05
61) Best_v2_shift_1e_05
62) Best_v2_shift_9e_06
63) Best_v2_only_OHWX
64) Best_v2_shift_value_1