VictorMylle
0 Followers · 0 Following
  • Joined on 2020-11-27
Repositories
6
 Projects Packages Public Activity Starred Repositories
VictorMylle synced commits to refs/pull/2198/head at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-21 02:53:00 +00:00
e7b8e9a778 doc: add --vae_chunk_size option for training and inference
f41e9e2b58 feat: add vae_chunk_size argument for memory-efficient VAE decoding and processing
Compare 2 commits »
VictorMylle synced commits to refs/pull/2198/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-21 02:53:00 +00:00
c542526dc3 Merge e7b8e9a778 into f5d44fd487
e7b8e9a778 doc: add --vae_chunk_size option for training and inference
f41e9e2b58 feat: add vae_chunk_size argument for memory-efficient VAE decoding and processing
Compare 3 commits »
VictorMylle synced commits to feat-hunyuan-image-2.1-inference at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-21 02:52:59 +00:00
e7b8e9a778 doc: add --vae_chunk_size option for training and inference
f41e9e2b58 feat: add vae_chunk_size argument for memory-efficient VAE decoding and processing
Compare 2 commits »
VictorMylle synced commits to refs/pull/2198/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-20 18:43:03 +00:00
daa70a9867 Merge 8f20c37949 into f5d44fd487
8f20c37949 feat: add --text_encoder_cpu option to reduce VRAM usage by running text encoders on CPU for training
b090d15f7d feat: add multi backend attention and related update for HI2.1 models and scripts
Compare 3 commits »
VictorMylle synced commits to refs/pull/2198/head at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-20 18:43:03 +00:00
8f20c37949 feat: add --text_encoder_cpu option to reduce VRAM usage by running text encoders on CPU for training
b090d15f7d feat: add multi backend attention and related update for HI2.1 models and scripts
Compare 2 commits »
VictorMylle synced commits to feat-hunyuan-image-2.1-inference at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-20 18:43:03 +00:00
8f20c37949 feat: add --text_encoder_cpu option to reduce VRAM usage by running text encoders on CPU for training
b090d15f7d feat: add multi backend attention and related update for HI2.1 models and scripts
Compare 2 commits »
VictorMylle synced commits to refs/pull/2198/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-18 17:43:02 +00:00
beb1883e04 Merge f834b2e0d4 into f5d44fd487
f834b2e0d4 fix: --fp8_vl to work
f6b4bdc83f feat: block-wise fp8 quantization
2ce506e187 fix: fp8 casting not working
Compare 4 commits »
VictorMylle synced commits to refs/pull/2198/head at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-18 17:43:01 +00:00
f834b2e0d4 fix: --fp8_vl to work
f6b4bdc83f feat: block-wise fp8 quantization
2ce506e187 fix: fp8 casting not working
Compare 3 commits »
VictorMylle synced commits to feat-hunyuan-image-2.1-inference at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-18 17:43:01 +00:00
f834b2e0d4 fix: --fp8_vl to work
f6b4bdc83f feat: block-wise fp8 quantization
2ce506e187 fix: fp8 casting not working
Compare 3 commits »
VictorMylle synced commits to refs/pull/2198/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-17 17:13:05 +00:00
8b5b52f090 Merge f5b004009e into f5d44fd487
f5b004009e fix: correct tensor indexing in HunyuanVAE2D class for blending and encoding functions
Compare 2 commits »
VictorMylle synced commits to refs/pull/2198/head at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-17 17:13:04 +00:00
f5b004009e fix: correct tensor indexing in HunyuanVAE2D class for blending and encoding functions
VictorMylle synced commits to refs/pull/1894/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-17 17:13:04 +00:00
e2d8025c1c Merge d73f2db22c into f5d44fd487
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
4568631b43 docs: update README to reflect improved loading speed of .safetensors files
e1c666e97f Update library/safetensors_utils.py
8783f8aed3 feat: faster safetensors load and split safetensor utils
Compare 33 commits »
VictorMylle synced commits to feat-hunyuan-image-2.1-inference at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-17 17:13:03 +00:00
f5b004009e fix: correct tensor indexing in HunyuanVAE2D class for blending and encoding functions
VictorMylle synced commits to refs/pull/2141/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-17 09:03:10 +00:00
753ac5af98 Merge 12da080c65 into f5d44fd487
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
4568631b43 docs: update README to reflect improved loading speed of .safetensors files
e1c666e97f Update library/safetensors_utils.py
8783f8aed3 feat: faster safetensors load and split safetensor utils
Compare 18 commits »
VictorMylle synced commits to refs/pull/1991/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 16:43:03 +00:00
876af14d14 Merge 4c8ebf7293 into f5d44fd487
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
4568631b43 docs: update README to reflect improved loading speed of .safetensors files
e1c666e97f Update library/safetensors_utils.py
8783f8aed3 feat: faster safetensors load and split safetensor utils
Compare 33 commits »
VictorMylle synced commits to refs/pull/2198/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 16:43:03 +00:00
19594a2a45 Merge cbe2a9da45 into f5d44fd487
cbe2a9da45 feat: add conversion script for LoRA models to ComfyUI format with reverse option
f318ddaeea docs: update HunyuanImage-2.1 training guide with model download instructions and VRAM optimization settings (by Claude)
39458ec0e3 fix: update default values for guidance_scale, image_size, infer_steps, and flow_shift in argument parser
Compare 4 commits »
VictorMylle synced commits to refs/pull/2198/head at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 16:43:03 +00:00
cbe2a9da45 feat: add conversion script for LoRA models to ComfyUI format with reverse option
f318ddaeea docs: update HunyuanImage-2.1 training guide with model download instructions and VRAM optimization settings (by Claude)
39458ec0e3 fix: update default values for guidance_scale, image_size, infer_steps, and flow_shift in argument parser
Compare 3 commits »
VictorMylle synced commits to feat-hunyuan-image-2.1-inference at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 16:43:02 +00:00
cbe2a9da45 feat: add conversion script for LoRA models to ComfyUI format with reverse option
f318ddaeea docs: update HunyuanImage-2.1 training guide with model download instructions and VRAM optimization settings (by Claude)
39458ec0e3 fix: update default values for guidance_scale, image_size, infer_steps, and flow_shift in argument parser
Compare 3 commits »
VictorMylle synced commits to refs/pull/2186/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 08:33:06 +00:00
c03a6001e7 Merge b1b9dec980 into f5d44fd487
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
4568631b43 docs: update README to reflect improved loading speed of .safetensors files
e1c666e97f Update library/safetensors_utils.py
8783f8aed3 feat: faster safetensors load and split safetensor utils
Compare 18 commits »
VictorMylle synced commits to refs/pull/2003/merge at VictorMylle/Kohya-ss-sd-scripts from mirror 2025-09-16 08:33:06 +00:00
9e685a5f02 Merge e64dc05c2a into f5d44fd487
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
4568631b43 docs: update README to reflect improved loading speed of .safetensors files
e1c666e97f Update library/safetensors_utils.py
8783f8aed3 feat: faster safetensors load and split safetensor utils
Compare 18 commits »