mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
upped max_steps in v1-finetune.yaml and fixed TI docs to address #493
This commit is contained in:
parent
7708f4fb98
commit
5e433728b5
@ -105,5 +105,6 @@ lightning:
|
|||||||
|
|
||||||
trainer:
|
trainer:
|
||||||
benchmark: True
|
benchmark: True
|
||||||
max_steps: 4000
|
max_steps: 4000000
|
||||||
|
# max_steps: 4000
|
||||||
|
|
@ -18,21 +18,30 @@ To train, prepare a folder that contains images sized at 512x512 and execute the
|
|||||||
--init_word 'cat'
|
--init_word 'cat'
|
||||||
```
|
```
|
||||||
|
|
||||||
During the training process, files will be created in /logs/[project][time][project]/
|
During the training process, files will be created in
|
||||||
where you can see the process.
|
/logs/[project][time][project]/ where you can see the process.
|
||||||
|
|
||||||
Conditioning contains the training prompts
|
Conditioning contains the training prompts inputs, reconstruction the
|
||||||
inputs, reconstruction the input images for the training epoch samples, samples scaled for a sample of the prompt and one with the init word provided.
|
input images for the training epoch samples, samples scaled for a
|
||||||
|
sample of the prompt and one with the init word provided.
|
||||||
|
|
||||||
On a RTX3090, the process for SD will take ~1h @1.6 iterations/sec.
|
On a RTX3090, the process for SD will take ~1h @1.6 iterations/sec.
|
||||||
|
|
||||||
_Note_: According to the associated paper, the optimal number of images is 3-5. Your model may not converge if you use more images than that.
|
_Note_: According to the associated paper, the optimal number of
|
||||||
|
images is 3-5. Your model may not converge if you use more images than
|
||||||
|
that.
|
||||||
|
|
||||||
Training will run indefinitely, but you may wish to stop it before the heat death of the universe, when you find a low loss epoch or around ~5000 iterations.
|
Training will run indefinitely, but you may wish to stop it (with
|
||||||
|
ctrl-c) before the heat death of the universe, when you find a low
|
||||||
|
loss epoch or around ~5000 iterations. Note that you can set a fixed
|
||||||
|
limit on the number of training steps by decreasing the "max_steps"
|
||||||
|
option in configs/stable_diffusion/v1-finetune.yaml (currently set to
|
||||||
|
4000000)
|
||||||
|
|
||||||
**Running**
|
**Running**
|
||||||
|
|
||||||
Once the model is trained, specify the trained .pt or .bin file when starting dream using
|
Once the model is trained, specify the trained .pt or .bin file when
|
||||||
|
starting dream using
|
||||||
|
|
||||||
```
|
```
|
||||||
(ldm) ~/stable-diffusion$ python3 ./scripts/dream.py --embedding_path /path/to/embedding.pt --full_precision
|
(ldm) ~/stable-diffusion$ python3 ./scripts/dream.py --embedding_path /path/to/embedding.pt --full_precision
|
||||||
|
Loading…
Reference in New Issue
Block a user